Arrow Research search

Author name cluster

Min Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

65 papers
2 author rows

Possible papers

65

JBHI Journal 2026 Journal Article

DPGOK: A Deep Learning-Based Method for Protein Function Prediction by Fusing GO Knowledge With Protein Features

  • Qiurong Yang
  • Wenkang Wang
  • Wei Fan
  • Ruiqing Zheng
  • Min Li

Accurately predicting protein functions is critical for understanding disease mechanisms and discovering potential drug targets. Gene Ontology (GO), with its hierarchical and semantic information, provides valuable context that can be integrated to improve prediction accuracy. Recently, several existing methods have attempted to integrate GO knowledge with protein sequence features for function prediction. However, these methods ignore the fact that GO embeddings should be tailored to proteins to reflect protein-specific functional relevance. To address this limitation, we proposed DPGOK, a deep learning-based method that fused protein-aware GO representations with protein features for function prediction. DPGOK first learns GO semantic representations with a knowledge graph loss and further generates protein-aware GO embeddings under the guidance of protein features. Results show that DPGOK outperforms state-of-the-art methods across all GO domains. Additional experiments demonstrated that DPGOK is capable of discovering hierarchically deeper and more informative functions for target proteins. Ablation studies revealed that the knowledge graph loss we introduced contributes to more stable and semantically coherent GO representations across different domains. Finally, we find that the predictive performance can be further improved when DPGOK is combined with homology-based approaches.

Details DOI

YNIMG Journal 2026 Journal Article

Dual neural mechanisms of sustained response inhibition: Right-lateralized core control and left-lateralized adaptive support

  • Liyue Lin
  • Jiahe Sun
  • Wei Xiong
  • Jiayi Zhao
  • Yishu Chen
  • Min Li
  • Xi Li
  • Ruyan Jiao

Sustained inhibition is critical for adaptive behavioral control in complex environments, yet its neural underpinnings remain poorly understood. Using a sequence-selective stop-signal task, we hypothesized that increasing stop-signal delay (SSD) would elicit distinct behavioral dynamics and recruit dissociable neural systems supporting different stages of sustained inhibition. fMRI data from 26 participants across three SSD conditions (no-, short-, and long-delay), combined with an activation likelihood estimation (ALE) meta-analysis of 64 classical stop-signal studies, enabled us to contrast sustained and transient inhibition. Key behavioral results revealed a systematic decrease in response time (RT) with increasing SSD, while inhibition execution time (IT/ET) followed an inverted U-shaped pattern. Neuroimaging findings demonstrated that sustained inhibition engages a significantly broader bilateral network compared to transient inhibition, spanning prefrontal, parietal, and subcortical regions. Further analyses revealed a dual-mechanism inhibitory network in which early go-stop competition recruited bilateral inhibitory regions, with the left hemisphere providing complementary support, whereas late-stage emergency stopping relied primarily on a right-dominant prefrontal pathway. Together, these findings establish sustained inhibition as a distinct and dynamically organized control process, providing a novel framework for understanding how the brain flexibly regulates behavior under evolving temporal demands.

Details DOI

EAAI Journal 2026 Journal Article

Explainable risk prediction model for on-chain Ponzi schemes based on complex network features

  • Bin Liao
  • Tao Zhou
  • Tao Zhang
  • Min Li

With the proliferation of blockchain technology and cryptocurrencies, on-chain Ponzi schemes have become increasingly rampant, posing a severe threat to the security of the digital financial ecosystem. Although existing detection models have demonstrated continuous improvements in performance, they often suffer from insufficient explainability, failing to meet the transparency requirements of regulatory bodies and practical applications. To address this gap, this study proposes an explainable risk prediction model for on-chain Ponzi schemes that integrates complex network features. First, a directed weighted temporal graph is constructed based on raw on-chain transaction data to extract multi-scale network structural and behavioral features. Second, Random Oversampling techniques are employed to address the issue of extreme class imbalance, and a Stacking-based ensemble learning model is constructed. Experimental results demonstrate that, under a strict non-leakage evaluation setting, the proposed model achieves an Accuracy of 99. 77%, Precision of 97. 34%, F1-score of 92. 96%, and Area Under the Curve (AUC) of 97. 01% of 97. 01%, significantly outperforming mainstream baseline methods. Finally, through the introduction of Shapley Additive exPlanations (SHAP) for explainability analysis, the study reveals that Ponzi scheme nodes exhibit a low-cost operational pattern characterized by “high value density” and “automated split laundering” in transaction behavior, while topologically displaying a “disassortative mixing” structure marked by extreme unidirectional fund flows and a “center-harvesting-edge” predatory mechanism.

Details DOI

EAAI Journal 2026 Journal Article

FedTrustAug: Federated sparse trust augmentation for service recommendation

  • Maolan Zhang
  • Di Xiao
  • Min Li
  • Lvjun Chen
  • Zhuyang Yu

Service recommendation is a crucial task for online platforms aiming to provide personalized and satisfactory user experiences. However, previous methods fail to handle the isolated, private, and heterogeneous trust data when users’ information is scattered across multiple parties. In this article, we propose FedTrustAug, a novel framework that leverages federated learning and graph neural networks to augment federated sparse trust for service recommendation. FedTrustAug leverages both implicit trust and indirect trust to enrich local trust graphs, employing a trust-aware attention mechanism to extract high-order trust features. FedTrustAug also safeguards the privacy of users’ data by preventing the leakage of sensitive identifiers and applying Gaussian differential privacy to the gradients. Furthermore, FedTrustAug preserves the local graph structures with compressed trustee embeddings and further lowers the communication cost with gradient quantization. Our extensive experiments on four real-world datasets demonstrate FedTrustAug’s ability to achieve a trade-off among accuracy, privacy, and communication costs, harmonizing these imperatives’ triumvirate.

Details DOI

TCS Journal 2026 Journal Article

k-Submodular and approximately non-k-submodular maximization under p-system and ℓ knapsack constraints

  • Hanlu Ye
  • Heqing Li
  • Min Li
  • Yang Zhou
  • Qian Liu

This paper addresses the problem of k-submodular and approximately non-k-submodular maximization under p-system and ℓ knapsack constraints. For monotone k-submodular functions, we first propose a greedy algorithm, achieving a 1 ( 1 + ϵ ′ ) ( 1 + p + 2 ℓ ) -approximation and a 1 ( 1 + ϵ ′ ) ( 2 + p + 2 ℓ ) -approximation for non-monotone case, with the O ( n 2 ( 1 + k ) log ( 2 n ) log ( 1 + ϵ ′ ) ) time complexity, where ϵ′ is a very small positive number. We further introduce an improved algorithm that enhances the approximation ratio to 1 ( 1 + ϵ ′ + ϵ ′ 2 ) ( 1 + p + 7 4 ℓ ) and 1 ( 1 + ϵ ′ + ϵ ′ 2 ) ( 2 + p + 7 4 ℓ ), respectively, while reducing the time complexity to O ( n k log n ϵ ′ log ( 2 n ) ). For monotone k-submodular functions with curvature c, we obtain an approximation result of 1 ( 1 + ϵ ′ ) ( p + c + ϵ ′ + 7 4 ℓ ). Additionally, we provide an approximation guarantee of min { 1, 1 α ( 1 + ϵ ′ ) } 1 + 1 + ϵ α 2 ( 1 − ϵ ) [ ( 1 + ϵ ′ ) ( p + α ϵ ′ ) + 7 4 ℓ ] for ϵ-approximately α-weakly diminishing returns functions.

Details DOI

JBHI Journal 2026 Journal Article

MoChat: Joints-Grouped Spatio-Temporal Grounding Multimodal Large Language Model for Multi-Turn Motion Comprehension and Description

  • Jiawei Mo
  • Yixuan Chen
  • Rifen Lin
  • Yongkang Ni
  • Feng Liang
  • Min Zeng
  • Xiping Hu
  • Min Li

Despite continuous advancements in deep learning for understanding human motion, existing models often struggle to accurately identify action timing and specific body parts, typically supporting only single-round interaction. This limitation is particularly pronounced in home exercise monitoring, neurological disorder assessment, and rehabilitation, where precise motion analysis is crucial for ensuring exercise efficacy, detecting early signs of neurological conditions, and guiding personalized recovery programs. In this paper, we propose MoChat, a multimodal large language model capable of spatio-temporal grounding of human motion and multi-turn dialogue understanding. To achieve this, we first group spatial features in skeleton frames according to human anatomical structures and process them through a Joints-Grouped Skeleton Encoder. The encoder’s outputs are fused with large language model embeddings to generate spatio-aware representations. A cross-attention-based Regression Head module is then designed to align hidden-layer embeddings and skeletal sequence embeddings, enabling precise temporal grounding. Furthermore, we develop a pipeline for temporal grounding task to extract timestamps from skeleton-text pairs and construct a multi-turn instruction dialogues for spatial grounding task. Finally, various task instructions are generated for jointly training. Experimental results demonstrate that MoChat achieves state-of-the-art performance across multiple metrics in motion understanding tasks, making it as the first model capable of fine-grained spatio-temporal grounding of human motion.

Details DOI

EAAI Journal 2026 Journal Article

Normality-enhanced knowledge distillation network for unsupervised industrial anomaly detection

  • Gang Li
  • Tianjiao Chen
  • Jin Wan
  • Mingle Zhou
  • Delong Han
  • Min Li

Applications in Engineering: Unsupervised Anomaly Detection (UAD) is essential for industrial surface defect detection since it eliminates the need for extensive and costly labeled data for training while effectively identifying previously unknown defects. Knowledge Distillation (KD)-based UAD has demonstrated effective results, which utilizes the feature differences between the teacher network (T-Net) and the student network (S-Net) to detect anomalies. However, existing methods struggle with normality forgetting and fail to capture subtle features of normal samples during the learning process, which hampers their ability to accurately detect anomalies. To address these issues, we propose a Normality-Enhanced Knowledge Distillation Network (NEKD). The contribution of artificial intelligence: Firstly, we propose a Memory Expert Mechanism (MEM) to strengthen the normality of features in the S-Net by recalling memorized normal feature information. Secondly, the Context-Aware Visual State Space (CA-VSS) block is proposed to enrich the feature representation of normal samples by extracting both global and local features. To enhance the S-Net’s ability to represent normal samples, we present a Dual-domain Consistency-constrained Loss (DCL) that constrains the feature distillation process. Extensive experiments on the MVTec Anomaly Detection (MVTec AD), BeanTech Anomaly Detection (BTAD), and MVTec 3D Anomaly Detection (MVTec 3D-AD), benchmark datasets demonstrate that our proposed method achieves state-of-the-art performance compared to other competitors.

Details DOI

AAAI Conference 2026 Conference Paper

Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification

  • Rifen Lin
  • Alex Jinpeng Wang
  • Jiawei Mo
  • Min Li

Multimodal pretraining has revolutionized visual understanding, but its impact on video-based person re-identification (ReID) remains underexplored. Existing approaches often rely on video-text pairs, yet suffer from two fundamental limitations: (1) lack of genuine multimodal pretraining, and (2) text poorly captures fine-grained temporal motion—an essential cue for distinguishing identities in video. In this work, we take a bold departure from text-based paradigms by introducing the first skeleton-driven pretraining framework for ReID. To achieve this, we propose Contrastive Skeleton-Image Pretraining for ReID (CSIP-ReID), a novel two-stage method that leverages skeleton sequences as a spatiotemporally informative modality aligned with video frames. In the first stage, we employ contrastive learning to align skeleton and visual features at sequence level. In the second stage, we introduce a dynamic Prototype Fusion Updater (PFU) to refine multimodal identity prototypes, fusing motion and appearance cues. Moreover, we propose a Skeleton Guided Temporal Modeling (SGTM) module that distills temporal cues from skeleton data and integrates them into visual features. Extensive experiments demonstrate that CSIP-ReID achieves new state-of-the-art results on standard video ReID benchmarks (MARS, LS-VID, iLIDS-VID). Moreover, it exhibits strong generalization to skeleton-only ReID tasks (BIWI, IAS), significantly outperforming previous methods. CSIP-ReID pioneers an annotation-free and motion-aware pretraining paradigm for ReID, opening a new frontier in multimodal representation learning.

PDF Details DOI

JBHI Journal 2025 Journal Article

Addressing Multiple Challenges in Early Gait Freezing Prediction for Parkinson's Disease: A Practical Deep Learning Approach

  • Wenan Wang
  • Jingfeng Lin
  • Xinning Le
  • Yaru Li
  • Tao Liu
  • Lunxin Pan
  • Min Li
  • Dezhong Yao

Objective: Freezing of Gait (FOG) significantly impacts daily activities of Parkinson's disease (PD) patients. Despite the potential of wearable sensors in predicting FOG, challenges persist, including the brief prediction interval before FOG onset, limited generalization across patients, and the inconvenience of multiple sensors. Addressing one issue often aggravates others, making it difficult to achieve suitable concurrent solutions to all these challenges. Methods: We introduce the PhysioGait Predictive Network (PhysioGPN), a deep learning framework designed to predict FOG events in PD patients at least 2 seconds prior to onset. The model architecture incorporates four key strategies: 1) Detection of progressive motion changes using large convolutional kernels; 2) Unraveling the complexity of motion coordination and gait dynamics using multi-dimensional and multi-scale convolution; 3) Capture gait self-similarity and asymmetry with twin-tower structure; 4) Promoting cross-domain information exchange with multi-domain attention. Furthermore, we propose a framework based on knowledge distillation (KD), reducing the model's dependence on multiple sensors while maintaining prediction accuracy. Results: The model achieves an 85. 8% Area Under the Curve (AUC) in FOG prediction. When reducing the number of sensors, KD mitigates the decline in performance and increases the AUC by 5. 1%, compared to scenarios without KD. Conclusion: Our research proposes a practical solution to the challenges of FOG prediction, demonstrating the effectiveness of the KD approach for lightweight wearable sensors in rehabilitation engineering. Significance: Our findings offer valuable insights for addressing multiple challenges in the practical application of wearable devices.

Details DOI

JBHI Journal 2025 Journal Article

CellCircLoc: Deep Neural Network for Predicting and Explaining Cell Line-Specific CircRNA Subcellular Localization

  • Min Zeng
  • Jingwei Lu
  • Yiming Li
  • Chengqian Lu
  • Shichao Kan
  • Fei Guo
  • Min Li

The subcellular localization of circular RNAs (circRNAs) is crucial for understanding their functional relevance and regulatory mechanisms. CircRNA subcellular localization exhibits variations across different cell lines, demonstrating the diversity and complexity of circRNA regulation within distinct cellular contexts. However, existing computational methods for predicting circRNA subcellular localization often ignore the importance of cell line specificity and instead train a general model on aggregated data from all cell lines. Considering the diversity and context-dependent behavior of circRNAs across different cell lines, it is imperative to develop cell line-specific models to accurately predict circRNA subcellular localization. In the study, we proposed CellCircLoc, a sequence-based deep learning model for circRNA subcellular localization prediction, which is trained for different cell lines. CellCircLoc utilizes a combination of convolutional neural networks, Transformer blocks, and bidirectional long short-term memory to capture both sequence local features and long-range dependencies within the sequences. In the Transformer blocks, CellCircLoc uses an attentive convolution mechanism to capture the importance of individual nucleotides. Extensive experiments demonstrate the effectiveness of CellCircLoc in accurately predicting circRNA subcellular localization across different cell lines, outperforming other computational models that do not consider cell line specificity. Moreover, the interpretability of CellCircLoc facilitates the discovery of important motifs associated with circRNA subcellular localization.

Details DOI

AAAI Conference 2025 Conference Paper

CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models

  • Zihui Cheng
  • Qiguang Chen
  • Jin Zhang
  • Hao Fei
  • Xiaocheng Feng
  • Wanxiang Che
  • Min Li
  • Libo Qin

Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and multi-modal reasoning output, aiming to mimic human-like reasoning that inherently integrates visual operation. Specifically, CoMT consists of four categories: (1) Visual Creation, (2) Visual Deletion, (3) Visual Update, and (4) Visual Selection to comprehensively explore complex visual operations and concise expression in real scenarios. We evaluate various LVLMs and strategies on CoMT, revealing some key insights into the capabilities and limitations of the current approaches. We hope that CoMT can inspire more research on introducing multi-modal generation into the reasoning process.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

  • Xiangyu Wen
  • Min Li
  • Junhua Huang
  • Jianyuan Zhong
  • Zhijian Xu
  • Zeju Li
  • Yongxiang Huang
  • Mingxuan Yuan

Large language models (LLMs) often produce reasoning steps that are superficially coherent yet internally inconsistent, leading to unreliable outputs. Since such failures typically arise from implicit or poorly-grounded knowledge, we introduce \emph{Grounded Reasoning in Dependency (GRiD)}, a novel dependency-aware reasoning framework that explicitly grounds reasoning steps in structured knowledge. GRiD represents reasoning as a graph consisting of interconnected knowledge extraction nodes and reasoning nodes, enforcing logical consistency through explicit dependencies. Each reasoning step is validated via a lightweight, step-wise verifier that ensures logical correctness relative to its premises. Extensive experiments across diverse reasoning benchmarks—including StrategyQA, CommonsenseQA, GPQA, and TruthfulQA—demonstrate that GRiD substantially improves reasoning accuracy, consistency, and faithfulness compared to recent state-of-the-art structured reasoning methods. Notably, GRiD enhances performance even when applied purely as a lightweight verification module at inference time, underscoring its generalizability and practical utility. Code is available at: https: //github. com/cure-lab/GRiD.

PDF Details

AAAI Conference 2025 Conference Paper

Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection

  • Libo Qin
  • Qiguang Chen
  • Jingxuan Zhou
  • Jin Wang
  • Hao Fei
  • Wanxiang Che
  • Min Li

Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-shot multi-intent detection. While significant advancements have been witnessed, the existing prompting approaches still face two major issues: lacking explicit reasoning and lacking interpretability. Therefore, in this paper, we introduce a Divide-Solve-Combine Prompting (DSCP) to address the above issues. Specifically, DSCP explicitly decomposes multi-intent detection into three components including (1) single-intent division prompting is utilized to decompose an input query into distinct sub-sentences, each containing a single intent; (2) intent-by-intent solution prompting is applied to solve each sub-sentence recurrently; and (3) multi-intent combination prompting is employed for combining each sub-sentence result to obtain the final multi-intent result. By decomposition, DSCP allows the model to track the explicit reasoning process and improve the interpretability. In addition, we propose an interactive divide-solve-combine prompting (Inter-DSCP) to naturally capture the interaction capabilities of large language models. Experimental results on two standard multi-intent benchmarks (i.e., MixATIS and MixSNIPS) reveal that both DSCP and Inter-DSCP obtain substantial improvements over baselines, achieving superior performance and higher interpretability.

PDF Details DOI

JBHI Journal 2025 Journal Article

DRGCL: Drug Repositioning via Semantic-Enriched Graph Contrastive Learning

  • Xiao Jia
  • Xinliang Sun
  • Kaili Wang
  • Min Li

Drug repositioning greatly reduces drug development costs and time by discovering new indications for existing drugs. With the development of technology and large-scale biological databases, computational drug repositioning has increasingly attracted remarkable attention, which can narrow down repositioning candidates. Recently, graph neural networks (GNNs) have been widely used and achieved promising results in drug repositioning. However, the existing GNNs based methods usually focus on modeling the complex drug-disease association graph, but ignore the semantic information on the graph, which may lead to a lack of consistency of global topology information and local semantic information for the learned features. To alleviate the above challenge, we propose a novel drug repositioning model based on graph contrastive learning, termed DRGCL. First, we treat the known drug-disease associations as the topology graph. Second, we select the top- $K$ similar neighbor from drug/disease similarity information to construct the semantic graph rather than use the traditional data augmentation strategy, thereby maximally retaining rich semantic information. Finally, we pull closer to embedding consistency of the different embedding spaces by graph contrastive learning to enhance the topology and semantic feature on the graph. We have evaluated DRGCL on four benchmark datasets and the experiment results show that the proposed DRGCL is superior to the state-of-the-art methods. Especially, the average result of DRGCL is 11. 92% higher than that of the second-best method in terms of AUPRC. The case studies further demonstrate the reliability of DRGCL.

Details DOI

EAAI Journal 2025 Journal Article

Dynamic scheduling in flexible and hybrid disassembly systems with manual and automated workstations using reward-shaping enhanced reinforcement learning

  • Jinlong Wang
  • Qihuiyang Liang
  • Min Li
  • Zelin Qu
  • Yuanyuan Zhang

As e-waste grows at an alarming rate, efficient disassembly systems have become crucial for sustainable production practices. Existing disassembly systems rely heavily on fixed automation and limited manual intervention, making it challenging to adapt to dynamic issues such as workstation failures and system bottlenecks, leading to inefficiencies and suboptimal resource allocation. To address these issues, a hybrid disassembly system is developed that integrates manual and automated workstations, allowing for the flexible variation of manual resources as needed to optimize the disassembly process, with a focus on reducing time and maximizing profit. Through the proposal of a Proximal Policy Optimization (PPO) algorithm enhanced with Reward-Shaping, the research effectively tackles key challenges of uncertainty and dynamic conditions in disassembly systems, including workstation failures and system bottlenecks. These issues are explored through a refrigerator disassembly simulation model. The results demonstrate that the PPO algorithm significantly outperforms traditional rule-based methods and two other reinforcement learning techniques in managing complex dynamic scheduling and resource allocation tasks, offering greater efficiency and flexibility. These findings contribute to the advancement of automated disassembly processes and their integration into modern industrial systems.

Details DOI

YNIMG Journal 2025 Journal Article

Expertise-related functional connectivity changes in Chinese calligraphy linked to flow experience

  • Qingyan Kong
  • Yue Wang
  • Min Li
  • Buxin Han
  • Rui Li

Flow is a deeply immersive state that supports optimal performance, yet its neural basis under conditions of real-world expertise remains poorly understood. Using functional MRI, this study investigated how long-term Chinese calligraphy expertise relates to flow in a culturally meaningful setting. Expert and novice participants performed imagined embodied handwriting of Kai-Shu and Cao-Shu, which differ in motor and cognitive challenges. Expert calligraphers reported significantly higher flow than novices across both scripts, including in the more challenging Cao-Shu style despite having no formal training in it. Functional connectivity analyses were performed on background task-residual BOLD signals to assess intrinsic coupling that persists during performance. In Kai-Shu, experts showed stronger ventral anterior insula (vAI)-superior parietal lobule (SPL) connectivity and weaker vAI-ventral striatum (VS) connectivity, suggesting enhanced perception-action coupling and reduced task-irrelevant processing. In Cao-Shu, experts exhibited reduced anterior medial prefrontal cortex (aMPFC) connectivity with default mode network (DMN) regions, suggesting reduced self-referential processing under higher task challenges. These connectivity patterns were significantly associated with reported flow ratings and together suggest a flexible neural adaptation supporting task-focused engagement in familiar contexts and reduced introspection when demands increase. To further examine whether these effects form an integrated mechanism linking proficiency and flow, Bayesian network (BN) modeling revealed a directional dependency from expertise to functional connectivity to flow, suggesting that long-term practice contributes to a proficient neural mechanism that supports higher flow experiences during task engagement. These findings extend current accounts of flow by delineating how sustained expertise is associated with neural processing patterns that are linked to higher flow across varying task challenges.

Details DOI

EAAI Journal 2025 Journal Article

GOM-MMOEA: Multimodal multi-objective evolutionary algorithm based on global orchestration mechanism

  • Shaobo Deng
  • Hui Shi
  • Hangyu Liu
  • Jinyu Xu
  • Sujie Guan
  • Min Li
  • Zhuolei Duan

The core challenge of multimodal multi-objective optimization lies in identifying and discovering multiple equivalent sets of Pareto-optimal solutions, thereby offering diverse options for decision-makers. However, most existing algorithms suffer from premature convergence when tackling such problems. This issue often arises due to inadequate population diversity and ineffective global exploration mechanisms during the search process, which causes the algorithm to become trapped in local optima and hinders the exploration of other promising regions in the decision space. To address this challenge, this paper proposes a multimodal multi-objective evolutionary algorithm based on a global orchestration mechanism. First, the algorithm constructs and dynamically updates an orchestration vector to guide the search toward optimal solutions and accelerate population convergence. Second, an orchestration vector update strategy is designed to gradually diminish the influence of inferior solutions, thereby preventing convergence to local optima. During the early stages of evolution, larger increments are applied to high-quality solutions to speed up convergence, while these increments are gradually reduced over time to promote global exploration. Finally, a novel parent selection mechanism is introduced, which dynamically adjusts selection probabilities to optimize the search process while preserving population diversity. Moreover, the algorithm adopts a triple population synergistic orchestration method that simultaneously considers both the objective and decision spaces. Experimental results demonstrate that the proposed algorithm outperforms several state-of-the-art methods across a range of benchmark test problems.

Details DOI

NeurIPS Conference 2025 Conference Paper

Joint Modeling of fMRI and EEG Imaging Using Ordinary Differential Equation-Based Hypergraph Neural Networks

  • Yan Zhang
  • Yang Gao
  • Min Li

Fusing multimodal brain imaging has been a hot topic since different modalities of brain imaging can provide complementary information. However, due to the size of simultaneous recorded fMRI-EEG dataset being limited and the substantial discrepancy between hemodynamic responses of fMRI and neural oscillations of EEG, the joint modeling of fMRI and EEG images is a rarely explored area and has not yielded satisfactory results. Existing studies have also indicated that the relationships between region of interest (ROI) are not one-to-one when synchronizing fMRI and EEG. Current graph-based multimodal modeling methods overlook those information. Based on this, we propose a hypergraph based fMRI-EEG modeling framework for asynchronous fMRI-EEG data named FE-NET. To the best of our knowledge, this is the first attempt to jointly model asynchronous EEG and fMRI data as Neural ODEs based hypergraph. Extensive experiments have demonstrated that the proposed FE-NET outperforms many state-of-the-art brain imaging modeling methods. Meanwhile, compared to simultaneously recorded fMRI-EEG data, asynchronously acquired fMRI-EEG data is less costly, which demonstrates the practical applicability of our method.

PDF Details

EAAI Journal 2025 Journal Article

MemMambaAD: Memory-augmented state space model for multivariate time series anomaly detection

  • Gang Li
  • Mingchao Ge
  • Jin Wan
  • Delong Han
  • Min Li
  • Mingle Zhou

Multivariate time series anomaly detection focuses on recognizing abnormal patterns to reduce system failures and improve production efficiency and product quality. Accurately detecting anomalies in data remains challenging because existing reconstruction-based methods are prone to overfitting. Recently, reconstruction methods guided by memory modules have been used to address this issue. However, these methods still suffer from insufficient feature extraction of time series prototypes and inadequate storage of normal sample prototype patterns in memory modules. To address these issues, we propose a memory-augmented state space model for multivariate time series anomaly detection. Specifically, we introduce a sequence decomposition state space model-temporal convolutional encoder, which independently extracts trend and seasonal features of multivariate time series in global and local manner, capturing the intrinsic patterns of time series more comprehensively. In addition, we propose a dynamic memory update mechanism, which flexibly updates the memory item through the memory selection mechanism, to more accurately record the prototype pattern of normal samples to improve anomaly detection performance. Extensive experiments on five benchmark datasets demonstrate that our method achieves state-of-the-art performance and reduces memory usage compared with other methods.

Details DOI

EAAI Journal 2025 Journal Article

Multi-echelon inventory optimization of waste electrical and electronic equipment closed-loop supply chain based on reinforcement learning under carbon tax policy

  • Jinlong Wang
  • Shangzhuo Zhou
  • Min Li
  • Guanyu Ren
  • Xianquan Ren
  • Xiaoyun Xiong
  • Yuanyuan Zhang

In response to environmental challenges posed by waste electrical and electronic equipment (WEEE), the WEEE closed-loop supply chain (CLSC) has emerged as a crucial means to promote circular economy through the recycling and reuse of WEEE, which not only reduces waste emissions but also improves the efficiency of resource utilization. In practice, both economic and environmental benefits must be considered in sustainable manufacturing within the CLSC to ensure the sustainable development of enterprises. Therefore, a multi-echelon, multi-period inventory model for the CLSC under carbon tax policy is developed in this paper, which innovatively introduces the carbon footprint to assess environmental impact and integrates the impacts of collection planning and the uncertainty of recycling quantity and product demand on the system, aiming to minimize total enterprise costs. To address the uncertainties in the model, the Proximal Policy Optimization (PPO) algorithm is employed to train a reinforcement learning (RL) agent. This agent enables enterprises to dynamically adjust internal strategies such as collection and production, as well as external procurement strategies, based on inventory levels and market conditions. By internalizing carbon emission costs through the carbon tax rate, the RL agent optimizes total costs while achieving a balance between economic and environmental benefits. Numerical experiments demonstrate that the PPO algorithm outperforms the traditional inventory management policy in terms of both cost control and carbon footprint reduction. Moreover, the moderate carbon tax policy on the CLSC appropriately increases the cost of enterprises while significantly reducing their carbon footprint and promoting sustainable development.

Details DOI

JBHI Journal 2025 Journal Article

Multiclass Classification Framework of Motor Imagery EEG by Riemannian Geometry Networks

  • Yuxuan Shi
  • Aimin Jiang
  • Ju Zhong
  • Min Li
  • Yanping Zhu

In motor imagery (MI) tasks for brain computer interfaces (BCIs), the spatial covariance matrix (SCM) of electroencephalogram (EEG) signals plays a critical role in accurate classification. Given that SCMs are symmetric positive definite (SPD), Riemannian geometry is widely utilized to extract classification features. However, calculating distances between SCMs is computationally intensive due to operations like eigenvalue decomposition, and classical optimization techniques, such as gradient descent, cannot be directly applied to Riemannian manifolds, making the computation of the Riemannian mean more complex and reliant on iterative methods or approximations. In this paper, we propose a novel multiclass classification framework that integrates Riemannian geometry and neural networks to mitigate these challenges. The framework comprises two modules: a Riemannian module with multiple branches and a classification module. During training, a fusion loss function is introduced to update the branch corresponding to the true label, while other branches are updated using different loss functions along with the classification module. Comprehensive experiments on four sets of MI EEG data demonstrate the efficiency and effectiveness of the proposed model.

Details DOI

YNIMG Journal 2025 Journal Article

Neural representation of trustworthiness encoding and inference in crowds

  • Renhao Liu
  • Dongfang Zhao
  • Xinlan Xu
  • Xiaoyu Zhang
  • Yuanyuan Yang
  • Min Li
  • Weiqi He

Trustworthiness perception is essential for social decision-making, yet its neural mechanisms, particularly in crowd contexts, remain unclear. This study examines the neural dynamics of crowd trustworthiness perception using EEG decoding and deep learning-based interpretability methods. The behavioral results demonstrate that ensemble coding enables stable trustworthiness judgments of crowds. In multivariate EEG analysis, crowd trustworthiness was decoded earlier than single trustworthiness, indicating that ensemble coding accelerates social impression formation. Cross-decoding further revealed shared neural representations between crowd and single trustworthiness, suggesting that ensemble coding does not fundamentally alter the nature of trustworthiness inference, but rather provides input to a shared high-level social cognitive system through early integration of facial features. Explainable analysis based on SHAP identified both distinct and similar channels in crowd and single face processing, with central-parietal regions playing a prominent role. These findings provide novel insights into the cognitive and neural mechanisms of high-level crowd social impression formation, offering a data-driven framework for multi-dimension decoding.

Details DOI

EAAI Journal 2025 Journal Article

Scene text image super-resolution with semantic-aware interaction

  • Mingle Zhou
  • Wenlong Liu
  • Jin Wan
  • Delong Han
  • Min Li
  • Gang Li

Scene text image super-resolution aims to enhance the resolution of images containing text in various scenes, which amplifies the prominence of the text and improves its recognizability. Existing methods struggle to accurately localize text regions in high-noise environments, which hampers their ability to effectively implement targeted super-resolution. To address these issues, we propose a Text image Super-resolution Semantic-aware Interaction Network (TSSIN) by embedding a text region segmentation network. First, we propose to use a pre-trained text region segmentation network (TRSN) to extract text region information. This approach semantically guides our model to address the challenge of the model not performing targeted super-resolution processing of text in high-noise environments. Secondly, we propose a multi-modal semantic information interaction module (MSIIM) to mitigate the issue of insufficient global information exchange. Comprehensive experiments conducted on the TextZoom dataset demonstrate that our TSSIN significantly enhances image quality. Furthermore, it shows a clear superiority over state-of-the-art methods on TextZoom, achieving an average text recognition accuracy improvement of +1. 0% over Transformer-Based Super-Resolution Network (TBSRN) (49. 6%, 56. 2%, 60. 1% vs. 48. 1%, 55. 9%, 58. 9%), +0. 83% over Parallelly Contextual Attention Network (PCAN), and +1. 46% over Text Prior Guided Super-Resolution (TPGSR), as evaluated by three pre-trained text recognition models. Code is available at https: //github. com/ads2d/TSSIN.

Details DOI

NeurIPS Conference 2025 Conference Paper

Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics

  • Jiayuan Ding
  • Jianhui Lin
  • Shiyu Jiang
  • Yixin Wang
  • Ziyang Miao
  • Zhaoyu Fang
  • Jiliang Tang
  • Min Li

Foundation models (FMs) have shown great promise in single-cell genomics, yet current approaches, such as scGPT, Geneformer, and scFoundation, rely on centralized training and language modeling objectives that overlook the tabular nature of single-cell data and raise significant privacy concerns. We present TABULA, a foundation model designed for single-cell transcriptomics, which integrates a novel tabular modeling objective and federated learning framework to enable privacy-preserving pretraining across decentralized datasets. TABULA directly models the cell-by-gene expression matrix through column-wise gene reconstruction and row-wise cell contrastive learning, capturing both gene-level relationships and cell-level heterogeneity without imposing artificial gene sequence order. Extensive experiments demonstrate the effectiveness of TABULA: despite using only half the pretraining data, TABULA achieves state-of-the-art performance across key tasks, including gene imputation, perturbation prediction, cell type annotation, and multi-omics integration. It is important to note that as public single-cell datasets continue to grow, TABULA provides a scalable and privacy-aware foundation that not only validates the feasibility of federated tabular modeling but also establishes a generalizable framework for training future models under similar privacy-preserving settings.

PDF Details

AIIM Journal 2025 Journal Article

TDMFS: Tucker decomposition multimodal fusion model for pan-cancer survival prediction

  • Jinchao Chen
  • Pei Liu
  • Chen Chen
  • Ying Su
  • Enguang Zuo
  • Min Li
  • Jiajia Wang
  • Ziwei Yan

Integrated analysis of multimodal data offers a more comprehensive view for cancer survival prediction, yet it faces challenges like computational intensity, overfitting, and challenges in achieving a unified representation due to data heterogeneity. To address the above issues, the first Tucker decomposition multimodal fusion model was hereby proposed for pan-cancer survival prediction (TDMFS). The model employed Tucker decomposition to limit complex tensor parameters during fusion, achieving deep modality integration with reduced computational cost and lower overfitting risk. The individual modality-specific representations were then fully exploited by signal modulation mechanisms in a bilinear pooling decomposition to serve as complementary information for the deep fusion representation. Furthermore, the performance of TDMFS was evaluated using a 5-fold cross-validation method with two modal data, gene expression (GeneExpr), and copy number variation (CNV), for 33 cancers from The Cancer Genome Atlas (TCGA) database. The experiments demonstrated that the proposed TDMFS model achieved an average C-index of 0. 757 across 33 cancer datasets, with a C-index exceeding 0. 80 on 10 of these datasets. Survival curves for both high and low risk patients plotted on 27 cancer datasets were statistically significant. The TDMFS model demonstrated superior performance in survival prediction, outperforming models like LinearSum and Multimodal Factorisation Higher Order Pooling, making it a valuable asset for advancing clinical cancer research.

Details DOI

JBHI Journal 2025 Journal Article

TransScore: A Graph Model for Pose Scoring and Affinity Prediction Based on Transformer Convolution Network

  • Chuqi Lei
  • Wenkang Wang
  • Wei Fan
  • Zhangli Lu
  • Jing Tang
  • Min Li

Predicting the interaction of protein and compound is an important task in drug discovery. Molecular docking has been a fundamental and vital computer-aid tool for digging potential interaction of the protein-compound pair. With the recent great success of artificial intelligence (AI), the scoring function, as a fundamental part of molecular docking, has been achieving much better performance by incorporating AI-based models. However, the AI-based models usually focus on a single prediction task (e. g. , affinity prediction), which is limited by their lack of extensibility. Moreover, the performance of AI-based models usually declines in cold start scenarios, thus compromising the robustness. To this end, we propose a novel deep learning-based graph model based on the transformer convolution network for pose scoring and affinity prediction. TransScore captures the intrinsic characteristics of protein-compound poses by employing the self-attention mechanism, which achieves superior performances in both cold and warm scenarios for the pose-scoring task. The outstanding performance is also shown in imbalanced datasets, which demonstrates the robustness of TransScore. In addition, the gated residual algorithm in TransScore enhances the model to adapt to diverse related tasks. In particular, in the affinity prediction task, we have observed consistent improvements in warm/cold start scenarios. Moreover, it is noticeable that TransScore excels in both accuracy and precision, accurately predicting affinities and their relative ordering. We also conducted an analysis on carbonic anhydrase II, which bears out that TransScore can elaborate the interaction mechanism of the protein-ligand pair, suggesting the potential application of TransScore in drug discovery.

Details DOI

EAAI Journal 2024 Journal Article

A differential evolution framework based on the fluid model for feature selection

  • Min Li
  • Junke Wang
  • Rutun Cao
  • Yulong Li

Feature selection in machine learning is a crucial step to effectively address the issue of feature redundancy in classification problems. Numerous feature selection algorithms have been developed to minimize the number of features, reduce computational cost, and improve classification accuracy. Differential evolution algorithms have the advantage of being simple in structure, robust, fast in convergence, and frequently used to solve feature selection problems. However, it is worth noting that differential evolution algorithms are susceptible to local optimum and stagnation issues, particularly when applied to high-dimensional data. To address this issue, in this study, we propose a differential evolution framework based on the fluid model, named DEF - F M, for feature selection. DEF - F M has the capability to speed up the convergence of differential evolution algorithms and alleviate the effects of local optima. The proposed framework is validated and compared against eight popular differential evolution algorithms using 12 publicly available benchmark datasets and experimental results unequivocally demonstrate the superiority of the proposed framework.

Details DOI

YNIMG Journal 2024 Journal Article

Altered white matter connectivity of ventral language networks in autism spectrum disorder: An automated fiber quantification analysis with multi-site datasets

  • Min Li
  • Maya Izumoto
  • Yide Wang
  • Yoko Kato
  • Yoshiko Iwatani
  • Ikuko Hirata
  • Yoshifumi Mizuno
  • Masaya Tachibana

Comprehension and pragmatic deficits are prevalent in autism spectrum disorder (ASD) and are potentially linked to altered connectivity in the ventral language networks. However, previous magnetic resonance imaging studies have not sufficiently explored the microstructural abnormalities in the ventral fiber tracts underlying comprehension dysfunction in ASD. Additionally, the precise locations of white matter (WM) changes in the long tracts of patients with ASD remain poorly understood. In the current study, we applied the automated fiber-tract quantification (AFQ) method to investigate the fine-grained WM properties of the ventral language pathway and their relationships with comprehension and symptom manifestation in ASD. The analysis included diffusion/T1 weighted imaging data of 83 individuals with ASD and 83 age-matched typically developing (TD) controls. Case-control comparisons were performed on the diffusion metrics of the ventral tracts at both the global and point-wise levels. We also explored correlations between diffusion metrics, comprehension performance, and ASD traits, and conducted subgroup analyses based on age range to examine developmental moderating effects. Individuals with ASD exhibited remarkable hypoconnectivity in the ventral tracts, particularly in the temporal portions of the left inferior longitudinal fasciculus (ILF) and the inferior fronto-occipital fasciculus (IFOF). These WM abnormalities were associated with poor comprehension and more severe ASD symptoms. Furthermore, WM alterations in the ventral tract and their correlation with comprehension dysfunction were more prominent in younger children with ASD than in adolescents. These findings indicate that WM disruptions in the temporal portions of the left ILF/IFOF are most notable in ASD, potentially constituting the core neurological underpinnings of comprehension and communication deficits in autism. Moreover, impaired WM connectivity and comprehension ability in patients with ASD appear to improve with age.

Details DOI

JBHI Journal 2024 Journal Article

Automated Prediction of Infant Cognitive Development Risk by Video: A Pilot Study

  • Shengjie Ji
  • Dan Ma
  • Lunxin Pan
  • Wenan Wang
  • Xiaohang Peng
  • Joan Toluwani Amos
  • Honorine Niyigena Ingabire
  • Min Li

Objective: Cognition is an essential human function, and its development in infancy is crucial. Traditionally, pediatricians used clinical observation or medical imaging to assess infants’ current cognitive development (CD) status. The object of pediatricians’ greater concern is however their future outcomes, because high-risk infants can be identified early in life for intervention. However, this opportunity has not yet been realized. Fortunately, some recent studies have shown that the general movement (GM) performance of infants around 3–4 months after birth might reflect their future CD status, which gives us an opportunity to achieve this goal by cameras and artificial intelligence. Methods: First, infants’ GM videos were recorded by cameras, from which a series of features reflecting their bilateral movement symmetry (BMS) were extracted. Then, after at least eight months of natural growth, the infants’ CD status was evaluated by the Bayley Infant Development Scale, and they were divided into high-risk and low-risk groups. Finally, the BMS features extracted from the early recorded GM videos were fed into the classifiers, using late infant CD risk assessment as the prediction target. Results: The area under the curve, recall and precision values reached 0. 830, 0. 832, and 0. 823 for two-group classification, respectively. Conclusion: This pilot study demonstrates that it is possible to automatically predict the CD of infants around the age of one year based on their GMs recorded early in life. Significance: This study not only helps clinicians better understand infant CD mechanisms, but also provides an economical, portable and non-invasive way to screen infants at high-risk early to facilitate their recovery.

Details DOI

AAAI Conference 2024 System Paper

Enhancing Machine Translation Experiences with Multilingual Knowledge Graphs

  • Simone Conia
  • Daniel Lee
  • Min Li
  • Umar Farooq Minhas
  • Yunyao Li

Translating entity names, especially when a literal translation is not correct, poses a significant challenge. Although Machine Translation (MT) systems have achieved impressive results, they still struggle to translate cultural nuances and language-specific context. In this work, we show that the integration of multilingual knowledge graphs into MT systems can address this problem and bring two significant benefits: i) improving the translation of utterances that contain entities by leveraging their human-curated aliases from a multilingual knowledge graph, and, ii) increasing the interpretability of the translation process by providing the user with information from the knowledge graph.

PDF Details DOI

EAAI Journal 2024 Journal Article

IDP-Net: Industrial defect perception network based on cross-layer semantic information guidance and context concentration enhancement

  • Gang Li
  • Shilong Zhao
  • Min Li
  • Mingle Zhou
  • Zuobin Ying

Applications in Engineering: In industry, surface defect detection is crucial for improving product quality. However, there are many challenges in industrial inspection scenarios, such as interference from background noise, complex small-target problems, significant variations in target objects, and the problem of finding a balance between inspection speed and accuracy. To address the above problems, this paper proposes an industrial defect-aware network based on cross-layer semantic information guidance and contextual attention enhancement (IDP-Net). Specifically, IDP-Net has four different new features. The contribution of artificial intelligence: Firstly, to solve the industrial surface context and defect similarity problem, this paper proposes a Lightweight Local Global Feature Extraction Network (LLG-Net), unlike other methods, the effective combination of self-attention blocks and convolution blocks ensures gradual integration of global and local features across multiple layers, to improve the detection ability of targets with significant changes in scale, this paper designs a Multiscale Perceptual Feature Aggregation Network (MPA-Net), adequately fuses the shallow fine-grained information and the deep semantic information. Then, to enhance the connection between multi-scale semantic information, an adaptive cross-layer feature fusion module (ACFF) is proposed, which is novel in integrating the characteristics of multiple adjacent levels to help the model better capture the different scale characterisation of the target. Finally, a Region Attention Module (RAM) is proposed and introduced in the detector to enhance the attention to the critical regions around the target object. In particular, this paper proposes a new localisation loss function (MEIoU) that enhances the network’s attention to objects at different scales. The experimental results show that 94. 3%, 98. 7% and 99. 5% of mAP@. 5 are obtained on steel, PCB and aluminium surface defect datasets, respectively, and 50 FPS is achieved, which is better than the current mainstream detectors and meets the demand of practical industrial production.

Details DOI

NeurIPS Conference 2024 Conference Paper

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

  • Alex Jinpeng Wang
  • Linjie Li
  • Yiqi Lin
  • Min Li
  • Lijuan Wang
  • Mike Zheng Shou

Training models with longer in-context lengths is a significant challenge for multimodal machine learning due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an innovative method designed to increase in-context text length in multi-modality large language models (MLLMs) efficiently. We present \ModelFullName (\ModelName), which processes long in-context text using visual tokens. This technique significantly reduces GPU memory usage and floating point operations (FLOPs). For instance, our method expands the pre-training in-context length from 256 to 2048 tokens with fewer FLOPs for a 56 billion parameter MOE model. Experimental results demonstrate that \ModelName enhances OCR capabilities and delivers superior performance on common downstream benchmarks for in-context few-shot evaluation. Additionally, \ModelName proves effective for long context inference, achieving results comparable to full text input while maintaining computational efficiency.

PDF Details DOI

IROS Conference 2024 Conference Paper

MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimation

  • Jiaqi Yang
  • Yucong Chen
  • Xiangting Meng
  • Chenxin Yan
  • Min Li
  • Ran Cheng
  • Lige Liu
  • Tao Sun

Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadvantage of such methods is that they require accurate depth maps which cannot be produced by consumer-grade sensors. Furthermore, many practical real-world situations involve a moving camera that continuously observes its surroundings, and the temporal information of the input video streams is simply overlooked by single-view methods. We propose a novel solution that makes use of RGB video streams. Our framework consists of three modules: a scale-aware monocular dense SLAM solution, a lightweight object pose predictor, and an object-level pose graph optimizer. The SLAM module utilizes a video stream and additional scale-sensitive readings to estimate camera poses and metric depth. The object pose predictor then generates canonical object representations from RGB images. The object pose is estimated through geometric registration of these canonical object representations with estimated object depth points. All per-view estimates finally undergo optimization within a pose graph, culminating in the output of robust and accurate canonical object poses. Our experimental results demonstrate that when utilizing public dataset sequences with high-quality depth information, the proposed method exhibits comparable performance to state-of-the-art RGB-D methods. We also collect and evaluate on new datasets containing depth maps of varying quality to further quantitatively benchmark the proposed method alongside previous RGB-D based methods. We demonstrate a significant advantage in scenarios where depth input is absent or the quality of depth sensing is limited.

Details

NeurIPS Conference 2024 Conference Paper

What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration

  • Libo Qin
  • Qiguang Chen
  • Hao Fei
  • Zhi Chen
  • Min Li
  • Wanxiang Che

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: " What factors affect the performance of MM-ICL? " To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research.

PDF Details DOI

EAAI Journal 2023 Journal Article

A large-scale MAGDM model based on SKNN and weighted clustering under incomplete information

  • Qianqian Wu
  • Donghong Tian
  • Ruike Lan
  • Min Li

Due to the complexity of multi-attribute group decision-making(MAGDM) problems, decision-makers frequently provide incomplete and hesitant evaluation information. How to make a valid decision based on incomplete and hesitant information is an important issue in MAGDM problems. Firstly, we novelly introduce a sequential K-nearest neighbor(SKNN) interpolation method to estimate the missing values based on the order of missing information proportions. When seeking the k-nearest neighbors of a decision-maker, an improved similarity measurement is proposed by considering the fuzzy-value similarity and the hesitation similarity between decision-makers simultaneously. Secondly, a K-means clustering algorithm based on attribute weighting is proposed to make the collective evaluation information more representative, and the attribute weights are obtained by constructing a mathematical model based on the minimum discrimination principle which can synthesize the subjective and objective weights information. Finally, an illustrative example and comparison analysis are demonstrated to show the validity and superiority of the proposed model.

Details DOI

YNIMG Journal 2023 Journal Article

Accurate and Efficient Simulation of Very High-Dimensional Neural Mass Models with Distributed-Delay Connectome Tensors

  • Anisleidy González Mitjans
  • Deirel Paz Linares
  • Carlos López Naranjo
  • Ariosky Areces Gonzalez
  • Min Li
  • Ying Wang
  • Ronaldo Garcia Reyes
  • Maria L. Bringas-Vega

This paper introduces methods and a novel toolbox that efficiently integrates high-dimensional Neural Mass Models (NMMs) specified by two essential components. The first is the set of nonlinear Random Differential Equations (RDEs) of the dynamics of each neural mass. The second is the highly sparse three-dimensional Connectome Tensor (CT) that encodes the strength of the connections and the delays of information transfer along the axons of each connection. To date, simplistic assumptions prevail about delays in the CT, often assumed to be Dirac-delta functions. In reality, delays are distributed due to heterogeneous conduction velocities of the axons connecting neural masses. These distributed-delay CTs are challenging to model. Our approach implements these models by leveraging several innovations. Semi-analytical integration of RDEs is done with the Local Linearization (LL) scheme for each neural mass, ensuring dynamical fidelity to the original continuous-time nonlinear dynamic. This semi-analytic LL integration is highly computationally-efficient. In addition, a tensor representation of the CT facilitates parallel computation. It also seamlessly allows modeling distributed delays CT with any level of complexity or realism. This ease of implementation includes models with distributed-delay CTs. Consequently, our algorithm scales linearly with the number of neural masses and the number of equations they are represented with, contrasting with more traditional methods that scale quadratically at best. To illustrate the toolbox's usefulness, we simulate a single Zetterberg-Jansen and Rit (ZJR) cortical column, a single thalmo-cortical unit, and a toy example comprising 1000 interconnected ZJR columns. These simulations demonstrate the consequences of modifying the CT, especially by introducing distributed delays. The examples illustrate the complexity of explaining EEG oscillations, e.g., split alpha peaks, since they only appear for distinct neural masses. We provide an open-source Script for the toolbox.

Details DOI

JBHI Journal 2023 Journal Article

CACO: A Core-Attachment Method With Cross-Species Functional Ortholog Information to Detect Human Protein Complexes

  • Wenkang Wang
  • Xiangmao Meng
  • Ju Xiang
  • Yunyan Shuai
  • Hayat Dino Bedru
  • Min Li

Protein complexes play an essential role in living cells. Detecting protein complexes is crucial to understand protein functions and treat complex diseases. Due to high time and resource consumption of experiment approaches, many computational approaches have been proposed to detect protein complexes. However, most of them are only based on protein-protein interaction (PPI) networks, which heavily suffer from the noise in PPI networks. Therefore, we propose a novel core-attachment method, named CACO, to detect human protein complexes, by integrating the functional information from other species via protein ortholog relations. First, CACO constructs a cross-species ortholog relation matrix and transfers GO terms from other species as a reference to evaluate the confidence of PPIs. Then, a PPI filter strategy is adopted to clean the PPI network and thus a weighted clean PPI network is constructed. Finally, a new effective core-attachment algorithm is proposed to detect protein complexes from the weighted PPI network. Compared to other thirteen state-of-the-art methods, CACO outperforms all of them in terms of F-measure and Composite Score, showing that integrating ortholog information and the proposed core-attachment algorithm are effective in detecting protein complexes.

Details DOI

JBHI Journal 2023 Journal Article

Fusion-Based Deep Learning Architecture for Detecting Drug-Target Binding Affinity Using Target and Drug Sequence and Structure

  • Kaili Wang
  • Min Li

Accurately predicting drug-target binding affinity plays a vital role in accelerating drug discovery. Many computational approaches have been proposed due to costly and time-consuming of wet laboratory experiments. In the input representation, most methods only focus on the target sequence properties or target structure properties while ignore the overall contribution. Therefore, we develop a novel fusion protocol based on multiscale convolutional neural networks and graph neural networks, named CGraphDTA, to predict drug-target binding affinity using target sequence and structure. Unlike existing methods, CGraphDTA is the first model constructed with target sequence and structure as input. Concretely, the multiscale convolutional neural networks are utilized to extract target and drug presentation from sequence, graph neural networks are employed to extract graph presentation from target and drug molecular structure. We compare CGraphDTA with the state-of-the-art methods, the results show that our model outperforms the current methods on the test sets. Furthermore, we conduct ablation studies, biological interpretation examination and drug selectivity evaluation, all results suggest that CGraphDTA is a useful tool to predict drug-target binding affinity and accelerate drug discovery.

Details DOI

EAAI Journal 2023 Journal Article

ICA-Net: Industrial defect detection network based on convolutional attention guidance and aggregation of multiscale features

  • Shilong Zhao
  • Gang Li
  • Mingle Zhou
  • Min Li

Detecting surface defects in the industry is essential for improving the quality of industrial products and maintaining product safety. However, problems such as the similarity of defects, significant variation in the scale of the target object, and the balance between detection speed and accuracy in industrial inspection scenarios have been considerable research topics in this field. This paper proposes an industrial defect detection network based on convolutional attention-guided and aggregated multiscale features to address these issues (ICA-Net). Firstly, for similarity defects in complex backgrounds, this paper proposes a backbone network with a combination of lightweight convolutional blocks and self-attentive modules to fully extract images’ local and global information and enhance the network’s expressiveness. Secondly, to make full use of the shallow fine-grained features and deep semantic features of the backbone network to improve the detection capability of defects with significant scale changes, this paper designs a cross-layer multiscale feature fusion network (CEF-Net), which fully fuses the features of adjacent layers and cross-layers through a reweighting feature strategy to enrich the network feature transfer path and ensure the efficient fusion of different scale features in the network. At the same time, the fine-grained feature fusion module (FFM) is used to fuse elements from multiple layers to extract more contextual information, enhance the extraction of fine-grained features and improve the detection capability of complex small targets. Finally, to address the problems of inaccurate regression localization and low detection accuracy of defects in existing industrial algorithms, a new IoU loss function (G-IOU) is proposed for regressing the intersection part of the predicted frame and the actual structure according to the aspect ratio of the real frame during the model regression to improve the accuracy and stability of detection. The experimental results show that 94. 1%, 98. 6%, 99. 4%, 98. 8% and 96. 5% of mAP@. 5 are obtained on steel, PCB, aluminium, automobile and Xsteel steel metal surface defect datasets, respectively, and 48 FPS is achieved, which is superior to the current mainstream detectors and meets the needs of practical industrial production.

Details DOI

EAAI Journal 2023 Journal Article

IDD-Net: Industrial defect detection method based on Deep-Learning

  • Zekai Zhang
  • Mingle Zhou
  • Honglin Wan
  • Min Li
  • Gang Li
  • Delong Han

Detecting defects in industrial products is one of the most widespread applications of industrial automation. Various product defects, large similarities, and drastic changes in scale in industrial scenarios pose challenges to existing industrial inspection networks. This paper proposes a deep learning-based industrial defect detection method (IDD-Net) to address the above challenges. Specifically, IDD-Net has three distinct features. First, for the defects of diversity and similarity (rolled-in_scale, crazing in steel defects), IDD-Net designed a novel local–global backbone feature network (LGB-Net). Second, IDD-Net proposes a novel Three-Layer Feature Aggregation network (TFLA-Net) to solve the problem of drastic scale changes. TFLA-Net adopts a novel three-layer descending method to aggregate semantic and fine-grained features effectively. At the same time, the dense connection of adjacent nodes of TFLA-Net ensures the efficient fusion of features of different scales in the network. In particular, this paper proposes a novel IoU loss (Defect-IoU loss) for the problem of object loss deviation at different scales. The novelty of Defect-IoU Loss is that the loss value is scaled by the difference in the area of different scale objects, which is more conducive to the balance of multi-scale object loss. The experimental results show that the calculation amount of IDD-Net is only 24. 9 Gflops, and the mAP@. 5 of 79. 66%, 99. 5%, and 95. 9% in the steel defect, aluminium defect, and PCB defect datasets were respectively obtained, surpassing all comparison models. In addition, the test in the actual industrial scene also demonstrates the feasibility of the application of IDD-Net.

Details DOI

IJCAI Conference 2023 Conference Paper

Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer

  • Yifan Wu
  • Shichao Kan
  • Min Zeng
  • Min Li

Transformers achieve excellent performance in a variety of domains since they can capture long-distance dependencies through the self-attention mechanism. However, self-attention is computationally costly due to its quadratic complexity and high memory consumption. In this paper, we propose a novel Transformer variant (Singularformer) that uses neural networks to learn the singular value decomposition process of the attention matrix to design a linear-complexity and memory-efficient global self-attention mechanism. Specifically, we decompose the attention matrix into the product of three matrix factors based on singular value decomposition and design neural networks to learn these matrix factors, then the associative law of matrix multiplication is used to linearize the calculation of self-attention. The above procedure allows us to compute self-attention as two-dimensional reduction processes in the first and second token dimensional spaces, followed by a multi-head self-attention computational process on the first dimensional reduced token features. Experimental results on 8 real-world datasets demonstrate that Singularformer performs favorably against the other Transformer variants with lower time and space complexity. Our source code is publicly available at https: //github. com/CSUBioGroup/Singularformer.

PDF Details DOI

AAAI Conference 2023 Conference Paper

UCoL: Unsupervised Learning of Discriminative Facial Representations via Uncertainty-Aware Contrast

  • Hao Wang
  • Min Li
  • Yangyang Song
  • Youjian Zhang
  • Liying Chi

This paper presents Uncertainty-aware Contrastive Learning (UCoL): a fully unsupervised framework for discriminative facial representation learning. Our UCoL is built upon a momentum contrastive network, referred to as Dual-path Momentum Network. Specifically, two flows of pairwise contrastive training are conducted simultaneously: one is formed with intra-instance self augmentation, and the other is to identify positive pairs collected by online pairwise prediction. We introduce a novel uncertainty-aware consistency K-nearest neighbors algorithm to generate predicted positive pairs, which enables efficient discriminative learning from large-scale open-world unlabeled data. Experiments show that UCoL significantly improves the baselines of unsupervised models and performs on par with the semi-supervised and supervised face representation learning methods.

PDF Details DOI

JBHI Journal 2022 Journal Article

A Pseudo Label-Wise Attention Network for Automatic ICD Coding

  • Yifan Wu
  • Min Zeng
  • Ying Yu
  • Yaohang Li
  • Min Li

Automatic International Classification of Diseases (ICD) coding is defined as a kind of text multi-label classification problem, which is difficult because the number of labels is very large and the distribution of labels is unbalanced. The label-wise attention mechanism is widely used in automatic ICD coding because it can assign weights to every word in full Electronic Medical Records (EMR) for different ICD codes. However, the label-wise attention mechanism is redundant and costly in computing. In this paper, we propose a pseudo label-wise attention mechanism to tackle the problem. Instead of computing different attention modes for different ICD codes, the pseudo label-wise attention mechanism automatically merges similar ICD codes and computes only one attention mode for the similar ICD codes, which greatly compresses the number of attention modes and improves the predicted accuracy. In addition, we apply a more convenient and effective way to obtain the ICD vectors, and thus our model can predict new ICD codes by calculating the similarities between EMR vectors and ICD vectors. Our model demonstrates effectiveness in extensive computational experiments. On the public MIMIC-III dataset and private Xiangya dataset, our model achieves the best performance on micro F1 (0. 583 and 0. 806), micro AUC (0. 986 and 0. 994), P@8 (0. 756 and 0. 413), and costs much smaller GPU memory (about 26. 1% of the models with label-wise attention). Furthermore, we verify the ability of our model in predicting new ICD codes. The interpretablility analysis and case study show the effectiveness and reliability of the patterns obtained by the pseudo label-wise attention mechanism.

Details DOI

JBHI Journal 2022 Journal Article

Analysis of ECG Signals by Dynamic Mode Decomposition

  • Honorine Niyigena Ingabire
  • Kangjia Wu
  • Joan Toluwani Amos
  • Sixuan He
  • Xiaohang Peng
  • Wenan Wang
  • Min Li
  • Jinying Chen

Objective: Based on cybernetics, a large system can be divided into subsystems, and the stability of each can determine the overall properties of the system. However, this stability analysis perspective has not yet been employed in electrocardiogram (ECG) signals. This is the first study to attempt to evaluate whether the stability of decomposed ECG subsystems can be analyzed in order to effectively investigate the overall performance of ECG signals, and aid in disease diagnosis. Methods: We used seven different cardiac pathologies (myocardial infarction, cardiomyopathy, bundle branch block, dysrhythmia, hypertrophy, myocarditis, and valvular heart disease) to illustrate our method. Dynamic mode decomposition (DMD) was first used to decompose ECG signals into dynamic modes (DMs) which can be regarded as ECG subsystems. Then, the features related to the DMs stabilities were extracted, and nine common classifiers were implemented for classification of these pathologies. Results: Most features were significant for differentiating the above-mentioned groups ( p value<0. 05 after Bonferroni correction). In addition, our method outperformed all existing methods for cardiac pathology classification. Conclusion: We have provided a new spatial and temporal decomposition method, namely DMD, to study ECG signals. Significance: Our method can reveal new cardiac mechanisms, which can contribute to the comprehensive understanding of its underlying mechanisms and disease diagnosis, and thus, can be widely used for ECG signal analysis in the future.

Details DOI

NeurIPS Conference 2022 Conference Paper

Coded Residual Transform for Generalizable Deep Metric Learning

  • Shichao Kan
  • Yixiong Liang
  • Min Li
  • Yigang Cen
  • Jianxin Wang
  • Zhihai He

A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability. Specifically, we learn a set of diversified prototype features, project the feature map onto each prototype, and then encode its features using their projection residuals weighted by their correlation coefficients with each prototype. The proposed CRT method has the following two unique characteristics. First, it represents and encodes the feature map from a set of complimentary perspectives based on projections onto diversified prototypes. Second, unlike existing transformer-based feature representation approaches which encode the original values of features based on global correlation analysis, the proposed coded residual transform encodes the relative differences between the original features and their projected prototypes. Embedding space density and spectral decay analysis show that this multi perspective projection onto diversified prototypes and coded residual representation are able to achieve significantly improved generalization capability in metric learning. Finally, to further enhance the generalization performance, we propose to enforce the consistency on their feature similarity matrices between coded residual transforms with different sizes of projection prototypes and embedding dimensions. Our extensive experimental results and ablation studies demonstrate that the proposed CRT method outperform the state-of-the-art deep metric learning methods by large margins and improving upon the current best method by up to 4. 28% on the CUB dataset.

PDF Details

YNIMG Journal 2022 Journal Article

Early protein energy malnutrition impacts life-long developmental trajectories of the sources of EEG rhythmic activity

  • Jorge Bosch-Bayard
  • Fuleah Abdul Razzaq
  • Carlos Lopez-Naranjo
  • Ying Wang
  • Min Li
  • Lidice Galan-Garcia
  • Ana Calzada-Reyes
  • Trinidad Virues-Alba

Protein Energy Malnutrition (PEM) has lifelong consequences on brain development and cognitive function. We studied the lifelong developmental trajectories of resting-state EEG source activity in 66 individuals with histories of Protein Energy Malnutrition (PEM) limited to the first year of life and in 83 matched classmate controls (CON) who are all participants of the 49 years longitudinal Barbados Nutrition Study (BNS). qEEGt source z-spectra measured deviation from normative values of EEG rhythmic activity sources at 5-11 years of age and 40 years later at 45-51 years of age. The PEM group showed qEEGt abnormalities in childhood, including a developmental delay in alpha rhythm maturation and an insufficient decrease in beta activity. These profiles may be correlated with accelerated cognitive decline.

Details DOI

YNIMG Journal 2022 Journal Article

Harmonized-Multinational qEEG norms (HarMNqEEG)

  • Min Li
  • Ying Wang
  • Carlos Lopez-Naranjo
  • Shiang Hu
  • Ronaldo César García Reyes
  • Deirel Paz-Linares
  • Ariosky Areces-Gonzalez
  • Aini Ismafairus Abd Hamid

This paper extends frequency domain quantitative electroencephalography (qEEG) methods pursuing higher sensitivity to detect Brain Developmental Disorders. Prior qEEG work lacked integration of cross-spectral information omitting important functional connectivity descriptors. Lack of geographical diversity precluded accounting for site-specific variance, increasing qEEG nuisance variance. We ameliorate these weaknesses. (i) Create lifespan Riemannian multinational qEEG norms for cross-spectral tensors. These norms result from the HarMNqEEG project fostered by the Global Brain Consortium. We calculate the norms with data from 9 countries, 12 devices, and 14 studies, including 1564 subjects. Instead of raw data, only anonymized metadata and EEG cross-spectral tensors were shared. After visual and automatic quality control, developmental equations for the mean and standard deviation of qEEG traditional and Riemannian DPs were calculated using additive mixed-effects models. We demonstrate qEEG "batch effects" and provide methods to calculate harmonized z-scores. (ii) We also show that harmonized Riemannian norms produce z-scores with increased diagnostic accuracy predicting brain dysfunction produced by malnutrition in the first year of life and detecting COVID induced brain dysfunction. (iii) We offer open code and data to calculate different individual z-scores from the HarMNqEEG dataset. These results contribute to developing bias-free, low-cost neuroimaging technologies applicable in various health settings.

Details DOI

JBHI Journal 2022 Journal Article

Multiparametric Quantitative US Examination of Liver Fibrosis: A Feature-Engineering and Machine-Learning Based Analysis

  • Huiying Wen
  • Wei Zheng
  • Min Li
  • Qing Li
  • Qiang Liu
  • Jianhua Zhou
  • Zhong Liu
  • Xin Chen

Quantitative ultrasound (QUS), which attempts to extract quantitative features from the US radiofrequency (RF) or envelope data for tissue characterization, is becoming a promising technique for noninvasive assessments of liver fibrosis. However, the number of feature variables examined and finally used in the existing QUS methods is typically small, limiting the diagnostic performance. Therefore, this paper devises a new multiparametric QUS (MP-QUS) method which enables the extraction of a large number of feature variables from US RF signals and allows for the use of feature-engineering and machine-learning based algorithms for liver fibrosis assessment. In the MP-QUS, eighty-four feature variables were extracted from multiple QUS parametric maps derived from the RF signals and the envelope data. Afterwards, feature reduction and selection were performed in turn to remove the feature redundancy and identify the best combination of features in the reduced feature set. Finally, a variety of machine-learning algorithms were tested for fibrosis classification with the selected features, based on the results of which the optimal classifier was established. The performance of the proposed MP-QUS method for staging liver fibrosis was evaluated on an animal model, with histologic examination as the reference standard. The mean accuracy, sensitivity, specificity and area under the receiver-operating-characteristic curve achieved by MP-QUS are respectively 83. 38%, 86. 04%, 80. 82%, and 0. 891 for recognizing significant liver fibrosis, and 85. 50%, 88. 92%, 85. 24%, and 0. 924 for diagnosing liver cirrhosis. The proposed MP-QUS method paves a way for its future extension to assess liver fibrosis in human subjects.

Details DOI

JBHI Journal 2022 Journal Article

Partner-Specific Drug Repositioning Approach Based on Graph Convolutional Network

  • Xinliang Sun
  • Bei Wang
  • Jie Zhang
  • Min Li

Drug repositioning identifies novel therapeutic potentials for existing drugs and is considered an attractive approach due to the opportunity for reduced development timelines and overall costs. Prior computational methods usually learned a drug's representation from an entire graph of drug-disease associations. Therefore, the representation of learned drugs representation are static and agnostic to various diseases. However, for different diseases, a drug's mechanism of actions (MoAs) are different. The relevant context information should be differentiated for the same drug to target different diseases. Computational methods are thus required to learn different representations corresponding to different drug-disease associations for the given drug. In view of this, we propose an end-to-end partner-specific drug repositioning approach based on graph convolutional network, named PSGCN. PSGCN firstly extracts specific context information around drug-disease pairs from an entire graph of drug-disease associations. Then, it implements a graph convolutional network on the extracted graph to learn partner-specific graph representation. As the different layers of graph convolutional network contribute differently to the representation of the partner-specific graph, we design a layer self-attention mechanism to capture multi-scale layer information. Finally, PSGCN utilizes sortpool strategy to obtain the partner-specific graph embedding and formulates a drug-disease association prediction as a graph classification task. A fully-connected module is established to classify the partner-specific graph representations. The experiments on three benchmark datasets prove that the representation learning of partner-specific graph can lead to superior performances over state-of-the-art methods. In particular, case studies on small cell lung cancer and breast carcinoma confirmed that PSGCN is able to retrieve more actual drug-disease associations in the top prediction results. Moreover, in comparison with other static approaches, PSGCN can partly distinguish the different disease context information for the given drug.

Details DOI

NeurIPS Conference 2022 Conference Paper

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

  • Chang Chen
  • Min Li
  • Zhihua Wu
  • Dianhai Yu
  • Chao Yang

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology. Based on communication modeling, we abstract the dispatch problem into an optimization objective and obtain the approximate dispatch pattern under different topologies. On top of that, we design a topology-aware auxiliary loss, which can adaptively route the data to fit in the underlying topology without sacrificing the model accuracy. Experiments show that TA-MoE can substantially outperform its counterparts on various hardware and model configurations, with roughly 1. 01x-1. 61x, 1. 01x-4. 77x, 1. 25x-1. 54x improvements over the popular DeepSpeed-MoE, FastMoE and FasterMoE systems.

PDF Details

TCS Journal 2022 Journal Article

The submodularity of two-stage stochastic maximum-weight independent set problems

  • Min Li
  • Hao Xiao
  • Qian Liu
  • Yang Zhou

In this paper, we extend the maximal independent set problem to two-stage stochastic case: given an independence system associated with one deterministic weight function and a random weight function, the goal is to find two nonoverlapping independent subsets from these two stages with the maximum total weight. In this paper, we study the submodularity of three kinds of two-stage independent set problems with max-weight. When the independent set problem is a matroid constraint, we can show its submodularity. However, neither submodular nor supermodular maximization problem can be obtained for the knapsack independent set problem by designing a counterexample. At last, we show that the robust two-stage stochastic maximum-weight uniform matroid problem can be formulated as a γ-submodular problem with cardinality constraint and also give a lower bound for γ.

Details DOI

TCS Journal 2021 Journal Article

Approximation algorithms for fuzzy C-means problem based on seeding method

  • Qian Liu
  • Jianxin Liu
  • Min Li
  • Yang Zhou

As a kind of important soft clustering model, the fuzzy C-means method is widely applied in many fields. In this method, instead of the strict distributive ability in the classical k-means method, all the sample points are endowed with degrees of membership to each center to depict the fuzzy clustering. In this paper, we show that the fuzzy C-means++ algorithm, which introduces the k-means++ algorithm as a seeding strategy, gives a solution for which the approximation guarantee is O ( k 2 ln ⁡ k ). A novel seeding algorithm is then designed based on the contribution of the fuzzy potential function, which improves the approximation ratio to O ( k ln ⁡ k ). Preliminary numerical experiments are proposed to support the theoretical results of this paper.

Details DOI

TCS Journal 2021 Journal Article

Approximation algorithms for spherical k-means problem using local search scheme

  • Dongmei Zhang
  • Yukun Cheng
  • Min Li
  • Yishui Wang
  • Dachuan Xu

In the spherical k-means problem (SKMP), which is a well-studied clustering problem in text mining, we are given an n-point set D in d-dimensional unit sphere S d, and an integer k ≤ n. The goal is to find a center subset S ⊂ S d with | S | ≤ k that minimizes the sum of cosine dissimilarity measure for each point in D to the nearest center. We prove that any γ-approximation algorithm for the k-means problem (KMP) can be adapted to the SKMP with 2γ-approximation ratio. It follows that there is a local search ( 18 + ϵ ) -approximation algorithm for the SKMP, by leveraging the classical local search ( 9 + ϵ ) -approximation algorithm for the KMP. Therefore, an interesting problem arises, that is whether there exists an approximation algorithm using local search scheme directly for the SKMP. In this paper, we present a local search approximation algorithm for the SKMP and prove its performance guarantee is ( 2 ( 4 + 7 ) + ϵ ). We also conduct numerical computation to show the efficiency of the local search approximation algorithm by single-swap operation in the end.

Details DOI

JBHI Journal 2021 Journal Article

Brain Network Analysis by Stable and Unstable EEG Components

  • Shengnan Liu
  • Min Li
  • Yukun Feng
  • Min Zhang
  • Mirabel Ewura Esi Acquah
  • Sunpei Huang
  • Jinying Chen
  • Peng Ren

Objective: Previous studies have already shown that electroencephalography (EEG) brain network (BN) can reflect the health status of individuals. However, novel methods are still needed for BN analysis. Therefore, in this study, BNs were constructed based on stable and unstable EEG components, and these may be implemented for disease diagnosis. Methods: Parkinson's disease (PD) was used as an example to illustrate this method. First, EEG signals were decomposed into dynamic modes (DMs). Each DM contains one eigenvalue that can determine not only the stability of that mode, but also its corresponding oscillatory frequency. Second, the stable and unstable components of EEG signals in each frequency band (delta, theta, alpha and beta) were calculated, which are based on the stable and unstable DMs within each respective frequency band. Third, newly developed BNs were constructed, including stable brain network (SBN), unstable brain network (UBN) and inter-connected brain network (IBN). Finally, their topological attributes were extracted in order to differentiate between PD patients and healthy controls (HC). Furthermore, topological attributes were also derived from traditional brain network (TBN) for comparison. Results: Most topological attributes of SBN, UBN and IBN can significantly differentiate between PD patients and HC (p value <; 0. 05). Furthermore, the area under the curve (AUC), precision and recall values of SBN analysis are all significantly higher than TBN. Conclusion: We proposed a new perspective on EEG BN analysis. Significance: These newly developed BNs not only have biological significance, but also could be widely applied in most medical and engineering fields.

Details DOI

EAAI Journal 2021 Journal Article

Construct a robust least squares support vector machine based on L p -norm and L ∞ -norm

  • Ting Ke
  • Lidong Zhang
  • Xuechun Ge
  • Hui Lv
  • Min Li

Despite some L p -norm LSSVMs own feature selection and prediction ability, they still suffer from two common issues. (i) They always ignore edge points because the L 2 -norm metric is used to measure the classification error of the training samples. The edge points are important in some practical application or on the datasets that are non-independent and identically distributed (non-i. i. d). (ii) They spend higher computational time and storage space for the large scale datasets. In order to solve the above two shortcomings while retaining the feature selection ability, we adopt L ∞ -norm to measure the classification error of training samples and still use L p -norm (0<p<1) to measure the maximum margin between two parallel support planes, then obtain a novel LSSVM classifier, denoted as L p -L ∞ -LSSVM. Our L p -L ∞ -LSSVM owns three advantages: (1) L ∞ -norm on empirical risk ensures the effective recognition of edge points, thereby improving the robustness and generalization ability of the classifier. (2) L p -norm on structural risk possess feature selection ability, whether for the linear or non-linear separable case and is suitable for the small samples size (SSS) problem. (3) Inspired by the sequential minimal optimization (SMO) algorithm, we designed an iterative heuristic algorithm by breaking the large quadratic programming problem (QPP) into a series of smallest possible QPPs, which can avoid high time-consuming. This algorithm not only ensures the convergence of optimum solution but also consumes lower computational time and storage space for large scale datasets. Finally, extensive numerical experiments once again verify the above opinions and show the outstanding classification performance and feature selection ability simultaneously.

Details DOI

JBHI Journal 2021 Journal Article

Deep Matrix Factorization Improves Prediction of Human CircRNA-Disease Associations

  • Chengqian Lu
  • Min Zeng
  • Fuhao Zhang
  • Fang-Xiang Wu
  • Min Li
  • Jianxin Wang

In recent years, more and more evidence indicates that circular RNAs (circRNAs) with covalently closed loop play various roles in biological processes. Dysregulation and mutation of circRNAs may be implicated in diseases. Due to its stable structure and resistance to degradation, circRNAs provide great potential to be diagnostic biomarkers. Therefore, predicting circRNA-disease associations is helpful in disease diagnosis. However, there are few experimentally validated associations between circRNAs and diseases. Although several computational methods have been proposed, precisely representing underlying features and grasping the complex structures of data are still challenging. In this paper, we design a new method, called DMFCDA (Deep Matrix Factorization CircRNA-Disease Association), to infer potential circRNA-disease associations. DMFCDA takes both explicit and implicit feedback into account. Then, it uses a projection layer to automatically learn latent representations of circRNAs and diseases. With multi-layer neural networks, DMFCDA can model the non-linear associations to grasp the complex structure of data. We assess the performance of DMFCDA using leave-one cross-validation and 5-fold cross-validation on two datasets. Computational results show that DMFCDA efficiently infers circRNA-disease associations according to AUC values, the percentage of precisely retrieved associations in various top ranks, and statistical comparison. We also conduct case studies to evaluate DMFCDA. All results show that DMFCDA provides accurate predictions.

Details DOI

TCS Journal 2021 Journal Article

Deterministic approximation algorithm for submodular maximization subject to a matroid constraint

  • Xin Sun
  • Dachuan Xu
  • Longkun Guo
  • Min Li

In this paper, we study the generalized submodular maximization problem with a non-negative monotone submodular set function as the objective function and subject to a matroid constraint. The problem is generalized through the curvature parameter α ∈ [ 0, 1 ] which measures how far a set function deviates from linearity to submodularity. We propose a deterministic approximation algorithm which uses the approximation algorithm proposed by Buchbinder et al. [2] as a building block and inherits the approximation guarantee for α = 1. For general value of the curvature parameter α ∈ [ 0, 1 ], we present an approximation algorithm with a factor of 1 + h α ( y ) + Δ ⋅ [ 3 + α − ( 2 + α ) y − ( 1 + α ) h α ( y ) ] 2 + α + ( 1 + α ) ( 1 − y ), where y ∈ [ 0, 1 ] is a predefined parameter for tuning the ratio. In particular, when α = 1 we obtain a ratio 0. 5008 when setting y = 0. 9, coinciding with the renowned state-of-art approximate ratio; when α = 0 that the object is a linear function, the approximation factor equals one and our algorithm is indeed an exact algorithm that always produces optimum solutions.

Details DOI

YNIMG Journal 2021 Journal Article

State-independent and state-dependent patterns in the rat default mode network

  • Wei Jing
  • Yang Xia
  • Min Li
  • Yan Cui
  • Mingming Chen
  • Miaomiao Xue
  • Daqing Guo
  • Bharat B. Biswal

Resting-state studies have typically assumed constant functional connectivity (FC) between brain regions, and these parameters of interest provide meaningful descriptions of the functional organization of the brain. A number of studies have recently provided evidence pointing to dynamic FC fluctuations in the resting brain, especially in higher-order regions such as the default mode network (DMN). The neural activities underlying dynamic FC remain poorly understood. Here, we recorded electrophysiological signals from DMN regions in freely behaving rats. The dynamic FCs between signals within the DMN were estimated by the phase locking value (PLV) method with sliding time windows across vigilance states [quiet wakefulness (QW) and slow-wave and rapid eye movement sleep (SWS and REMS)]. Factor analysis was then performed to reveal the hidden patterns within the DMN. We identified distinct spatial FC patterns according to the similarities between their temporal dynamics. Interestingly, some of these patterns were vigilance state-dependent, while others were independent across states. The temporal contributions of these patterns fluctuated over time, and their interactive relationships were different across vigilance states. These spatial patterns with dynamic temporal contributions and combinations may offer a flexible framework for efficiently integrating information to support cognition and behavior. These findings provide novel insights into the dynamic functional organization of the rat DMN.

Details DOI

NeurIPS Conference 2021 Conference Paper

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

  • Yu Li
  • Min Li
  • Qiuxia Lai
  • Yannan Liu
  • Qiang Xu

Deep learning (DL) systems are notoriously difficult to test and debug due to the lack of correctness proof and the huge test input space to cover. Given the ubiquitous unlabeled test data and high labeling cost, in this paper, we propose a novel test prioritization technique, namely TestRank, which aims at revealing more model failures with less labeling effort. TestRank brings order into the unlabeled test data according to their likelihood of being a failure, i. e. , their failure-revealing capabilities. Different from existing solutions, TestRank leverages both intrinsic and contextual attributes of the unlabeled test data when prioritizing them. To be specific, we first build a similarity graph on both unlabeled test samples and labeled samples (e. g. , training or previously labeled test samples). Then, we conduct graph-based semi-supervised learning to extract contextual features from the correctness of similar labeled samples. For a particular test instance, the contextual features extracted with the graph neural network and the intrinsic features obtained with the DL model itself are combined to predict its failure-revealing capability. Finally, TestRank prioritizes unlabeled test inputs in descending order of the above probability value. We evaluate TestRank on three popular image classification datasets, and results show that TestRank significantly outperforms existing test prioritization techniques.

PDF Details

JBHI Journal 2020 Journal Article

miRTMC: A miRNA Target Prediction Method Based on Matrix Completion Algorithm

  • Hui Jiang
  • Mengyun Yang
  • Xiang Chen
  • Min Li
  • Yaohang Li
  • Jianxin Wang

microRNAs (miRNAs) are small non-coding RNAs which modulate the stability of gene targets and their rates of translation into proteins at transcriptional level and post-transcriptional level. miRNA dysfunctions can lead to human diseases because of dysregulation of their targets. Correct miRNA target prediction will lead to better understanding of the mechanisms of human diseases and provide hints on curing them. In recent years, computational miRNA target prediction methods have been proposed according to the interaction rules between miRNAs and targets. However, these methods suffer from high false positive rates due to the complicated relationship between miRNAs and their targets. The rapidly growing number of experimentally validated miRNA targets enables predicting miRNA targets with high precision via accurate data analysis. Taking advantage of these known miRNA targets, a novel recommendation system model (miRTMC) for miRNA target prediction is established using a new matrix completion algorithm. In miRTMC, a heterogeneous network is constructed by integrating the miRNA similarity network, the gene similarity network, and the miRNA-gene interaction network. Our assumption is that the latent factors determining whether a gene is the target of miRNA or not are highly correlated, i. e. , the adjacency matrix of the heterogeneous network is low-rank, which is then completed by using a nuclear norm regularized linear least squares model under non-negative constraints. Alternating direction method of multipliers (ADMM) is adopted to numerically solve the matrix completion problem. Our results show that miRTMC outperforms the competing methods in terms of various evaluation metrics. Our software package is available at https://github.com/hjiangcsu/miRTMC.

Details DOI

JBHI Journal 2020 Journal Article

Predicting Human lncRNA-Disease Associations Based on Geometric Matrix Completion

  • Chengqian Lu
  • Mengyun Yang
  • Min Li
  • Yaohang Li
  • Fang-Xiang Wu
  • Jianxin Wang

Recently, increasing evidences reveal that dysregulations of long non-coding RNAs (lncRNAs) are relevant to diverse diseases. However, the number of experimentally verified lncRNA-disease associations is limited. Prioritizing potential associations is beneficial not only for disease diagnosis, but also disease treatment, more important apprehending disease mechanisms at lncRNA level. Various computational methods have been proposed, but precise prediction and full use of data's intrinsic structure are still challenging. In this work, we design a new method, denominated GMCLDA (Geometric Matrix Completion lncRNA-Disease Association), to infer underlying associations based on geometric matrix completion. Utilizing association patterns among functionally similar lncRNAs and phenotypically similar diseases, GMCLCA makes use of the intrinsic structure embedded in the association matrix. Besides, limiting the scope of the predicted values gives rise to a certain sparsity in computation and enhances the robustness of GMCLDA. GMCLDA computes disease semantic similarity according to the Disease Ontology (DO) hierarchy and lncRNA Gaussian interaction profile kernel similarity according to known interaction profiles. Then, GMCLDA measures lncRNA sequence similarity using Needleman-Wunsch algorithm. For a new lncRNA, GMCLDA prefills interaction profile on account of its K-nearest neighbors defined by sequence similarity. Finally, GMCLDA estimates the missing entries of the association matrix based on geometric matrix completion model. Compared with state-of-the-art methods, GMCLDA can provide more accurate lncRNA-disease prediction. Further case studies prove that GMCLDA is able to correctly infer possible lncRNAs for renal cancer.

Details DOI

TCS Journal 2019 Journal Article

Efficient approximation algorithms for maximum coverage with group budget constraints

  • Longkun Guo
  • Min Li
  • Dachuan Xu

Given a ground set U with a non-negative weight w i for each i ∈ U, a positive integer k and a collection of sets S, which is partitioned into a family of disjoint groups G, the goal of the Maximum Coverage problem with Group budget constraints (MCG) is to select k sets from S, such that the total weight of the union of the k sets is maximized and at most one set is selected from each group G ∈ G. We first present an approximation algorithm with a factor 1 − 1 e and an exponential time via randomized linear programming rounding technique. Then we improve the time complexity of the algorithm to O ( ( m + n ) 3. 5 L + k 3. 5 q 7 L ) for | S | = m, | U | = n, and L being the length of the input, by the key idea of modeling the selection of groups as computing a constrained flow in a corresponding auxiliary graph. The algorithm is later shown can be extended to solve two generalizations of MCG. Last but not the least, we present another algorithm with a time complexity O ( ( m + n ) 3. 5 L + k δ 10. 5 L ) and a slightly increased approximation ratio 1 − e 1 δ − 1 mainly based on the idea of partition, where δ ≥ 2 is a parameter tuning which can balance the time complexity and the ratio.

Details DOI

YNIMG Journal 2018 Journal Article

Abnormal frontostriatal tracts in young male tobacco smokers

  • Kai Yuan
  • Dahua Yu
  • Meng Zhao
  • Min Li
  • Ruonan Wang
  • Yangding Li
  • Peter Manza
  • Ehsan Shokri-Kojori

Dysfunctions in frontostriatal circuits have been associated with craving and cognitive control in smokers. However, the relevance of white matter (WM) diffusion properties of the ventral and dorsal frontostriatal tracts for behaviors associated with smoking remains relatively unknown, especially in young adulthood, a critical time period for the development and maintenance of addiction. Here, diffusion tensor imaging (DTI) and probabilistic tractography were used to investigate the WM tracts of the ventral and dorsal frontostriatal circuits in two independent studies (Study1: 36 male smokers (21. 3 ± 1. 3 years) vs. 35 male nonsmokers (21. 2 ± 1. 3 years); Study2: 29 male smokers (21. 4 ± 1. 1 years) vs. 25 male nonsmokers (21. 0 ± 1. 4 years)). Subjective craving was measured by the Questionnaire on Smoking Urges (QSU) and cognitive control ability was assessed with the Stroop task. In both studies, smokers committed more response errors than nonsmokers during the incongruent condition of the Stroop task. Relative to controls, smokers showed lower fractional anisotropy (FA) and higher radial diffusivity in left medial orbitofrontal cortex-to-nucleus accumbens fiber tracts (ventral frontostriatal path) and also lower FA in right dorsolateral prefrontal cortex-to-caudate fiber tracts (dorsal frontostriatal path). The FA values of the right dorsal fibers were negatively correlated with incongruent response Stroop errors in smokers, whereas the mean diffusivity values of the left ventral fibers were positively correlated with craving in smokers. Thus, WM diffusion properties of the dorsal and ventral frontostriatal tracts were associated with cognitive control and craving, respectively, in young male tobacco smokers. These data highlight the importance of studying WM in relation to neuropsychological changes underlying smoking.

Details DOI

AAAI Conference 2016 Conference Paper

EKNOT: Event Knowledge from News and Opinions in Twitter

  • Min Li
  • Jingjing Wang
  • Wenzhu Tong
  • Hongkun Yu
  • Xiuli Ma
  • Yucheng Chen
  • Haoyan Cai
  • Jiawei Han

We present the EKNOT system that automatically discovers major events from online news articles, connects each event to its discussion in Twitter, and provides a comprehensive summary of the events from both news media and social media’s point of view. EKNOT takes a time period as input and outputs a complete picture of the events within the given time range along with the public opinions. For each event, EKNOT provides multi-dimensional summaries: a) a summary from news for an objective description; b) a summary from tweets containing opinions/sentiments; c) an entity graph which illustrates the major players involved and their correlations; d) the time span of the event; and e) an opinion (sentiment) distribution. Also, if a user is interested in a particular event, he/she can zoom into this event to investigate its aspects (subevents) summarized in the same manner. EKNOT is built on real-time crawled news articles and tweets, allowing users to explore the dynamics of major events with minimal delays.

PDF Details

NeurIPS Conference 2015 Conference Paper

Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing

  • Tom Goldstein
  • Min Li
  • Xiaoming Yuan

The alternating direction method of multipliers (ADMM) is an important tool for solving complex optimization problems, but it involves minimization sub-steps that are often difficult to solve efficiently. The Primal-Dual Hybrid Gradient (PDHG) method is a powerful alternative that often has simpler substeps than ADMM, thus producing lower complexity solvers. Despite the flexibility of this method, PDHG is often impractical because it requires the careful choice of multiple stepsize parameters. There is often no intuitive way to choose these parameters to maximize efficiency, or even achieve convergence. We propose self-adaptive stepsize rules that automatically tune PDHG parameters for optimal convergence. We rigorously analyze our methods, and identify convergence rates. Numerical experiments show that adaptive PDHG has strong advantages over non-adaptive methods in terms of both efficiency and simplicity for the user.

PDF Details
v2026.09.13