Author name cluster

Jin Liu

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.

42 papers

2 author rows

JBHI Journal 2026 Journal Article

BS-LDM: Effective B one S uppression in High-Resolution Chest X-Ray Images With Conditional L atent D iffusion M odels

Yifei Sun
Zhanghao Chen
Hao Zheng
Wenming Deng
Jin Liu
Wenwen Min
Ahmed Elazab
Xiang Wan

Lung diseases represent a significant global health challenge, with Chest X-Ray (CXR) being a key diagnostic tool due to its accessibility and affordability. Nonetheless, the detection of pulmonary lesions is often hindered by overlapping bone structures in CXR images, leading to potential misdiagnoses. To address this issue, we develop an end-to-end framework called BS-LDM, designed to effectively suppress bone in high-resolution CXR images. This framework is based on conditional latent diffusion models and incorporates a multi-level hybrid loss-constrained vector-quantized generative adversarial network which is crafted for perceptual compression, ensuring the preservation of details. To further enhance the framework’s performance, we utilize offset noise in the forward process, and a temporal adaptive thresholding strategy in the reverse process. These additions help minimize discrepancies in generating low-frequency information of soft tissue images. Additionally, we have compiled a high-quality bone suppression dataset named SZCH-X-Rays. This dataset includes 818 pairs of high-resolution CXR and soft tissue images collected from our partner hospital. Moreover, we processed 241 data pairs from the JSRT dataset into negative images, which are more commonly used in clinical practice. Our comprehensive experiments and downstream evaluations reveal that BS-LDM excels in bone suppression, underscoring its clinical value.

AAAI Conference 2026 Conference Paper

Clustering with Self-Learned Graph Regression

Lai Wei
Jin Liu

Graph-based clustering algorithms aim to construct an affinity graph that accurately captures the intrinsic structure of a dataset. To achieve this goal, these algorithms often use the k-nearest-neighbor (k-nn) method to build a graph regularizer for the required affinity graph, enabling it to have a grouping effect. However, due to the complex nature of real-world data, the k-nn method often fails to capture the true neighborhood relationships of a dataset, which in turn limits the quality of the learned affinity graph. Motivated by the insight that a learned affinity graph itself can more effectively reflect the underlying data structure, we propose a new graph-based clustering method, termed Self-learned Graph Regression (SGR). Unlike traditional approaches, SGR constructs its graph regularizer directly from the affinity graph being learned, allowing the graph to adaptively capture more accurate structural information. To solve the proposed problem, we develop an optimization algorithm along with an acceleration strategy. We further analyze the convergence and computational complexity of the proposed algorithm. Extensive clustering experiments on various benchmark datasets demonstrate that our method outperforms the state-of-the-art graph-based clustering algorithms.

PDF Details DOI

AAAI Conference 2026 Conference Paper

CoGrad3D: Spatially-Coupled Timestep Optimization with Orthogonal Gradient Fusion for 3D Generation

Haoyang Tong
Hongbo Wang
Jin Liu
Qi Wang
Jie Cao
Ran He

Score Distillation Sampling has driven recent advances in text-to-3D generation. However, current approaches often fail to produce 3D assets that are both rich in detail and consistent across viewpoints. These limitations primarily arise from imbalanced guidance on fine-grained details and an overdependence on single-view optimization—issues exacerbated by the excessive randomness in selecting diffusion timesteps and camera configurations. Such deficiencies commonly lead to blurry textures and inter-view inconsistencies, which degrade visual realism and hinder practical deployment. To tackle these challenges, we introduce CoGrad3D, a unified generative refinement framework that adopts a continuously adaptive optimization strategy. By dynamically modulating the optimization focus based on real-time convergence signals, CoGrad3D ensures balanced progress toward both geometric completeness and high-fidelity detail. Concretely, we propose an adaptive region sampling strategy that emphasizes under-converged viewing areas, promoting stable and uniform optimization. To facilitate the transition from coarse geometry to fine-grained reconstruction, we develop a region-aware temporal scheduling scheme that integrates global training dynamics with local convergence feedback. Furthermore, we introduce a gradient fusion mechanism that consolidates historical gradients from adjacent viewpoints, mitigating view-specific artifacts and promoting the emergence of coherent 3D structures. Extensive experiments demonstrate that CoGrad3D substantially surpasses existing methods in both geometric consistency and texture fidelity, enabling the generation of high-quality, view-consistent 3D models from textual descriptions.

PDF Details DOI

JBHI Journal 2026 Journal Article

Customized SAM-Med3D With Multi-View Representation Fusion and Age-Grade Stratified Loss for Glioma Survival Risk Prediction

Xinyu Li
Hulin Kuang
Jin Liu
Lanlan Wang
Pengcheng Shu
Mengshen He
Jianxin Wang

Survival risk prediction is crucial for personalized treatment of gliomas. Medical image foundational models can explore complex medical features, which are critical for prognosis in gliomas. We propose SAM-Risk, which uses a customized SAM-Med3D with multi-view representation fusion and clinical knowledge-based age-grade stratified loss for glioma survival risk prediction. First, to utilize potential interactions between multiple views at an early stage, we design a 3D representation generation module that transforms 1D handcrafted radiomics and clinical features into 3D representations, which are fused with multimodal MRIs through a multi-view representation fusion module. The fused representation is fed into the customized SAM-Med3D, fine-tuned using LoRA and a disparity function to extract survival risk-related features. We design a feature refinement module to explore the inter-channel relationships among the outputs of the fine-tuned SAM-Med3D. Additionally, we propose an age-grade stratified loss based on glioma prognosis standards to make the predicted risk more consistent with clinical prior knowledge. Validated on two publicly available UCSF-PDGM and BraTS2020 datasets, SAM-Risk achieves a C-index of 75. 08% and 73. 67%, respectively, outperforming several survival risk prediction methods.

AAAI Conference 2026 Conference Paper

FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models

Junkang Liu
Fanhua Shang
Hongying Liu
Yuxuan Tian
Yuanyuan Liu
Jin Liu
Kewen Zhu
Zhouchen Lin

AdamW has become one of the most effective optimizers for training large-scale models. We have also observed its effectiveness in the context of federated learning (FL). However, directly applying AdamW in federated learning settings poses significant challenges: (1) due to data heterogeneity, AdamW often yields high variance in the second-moment estimate v; (2) the local overfitting of AdamW may cause client drift; and (3) Reinitializing moment estimates (v, m) at each round slows down convergence. To address these challenges, we propose the first Federated AdamW algorithm, called FedAdamW, for training and fine-tuning various large models. FedAdamW aligns local updates with the global update using both a local correction mechanism and decoupled weight decay to mitigate local overfitting. FedAdamW efficiently aggregates the mean of the second-moment estimates to reduce their variance and reinitialize them. Theoretically, we prove that FedAdamW achieves a linear speedup convergence rate of O（p（L∆σ2l ）/（SKRε2） + （L∆）/R） without heterogeneity assumption, where S is the number of participating clients per round, K is the number of local iterations, and R is the total number of communication rounds. We also employ PAC-Bayesian generalization analysis to explain the effectiveness of decoupled weight decay in local training. Empirically, we validate the effectiveness of FedAdamW on language and vision Transformer models. Compared to several baselines, FedAdamW significantly reduces communication rounds and improves test accuracy.

PDF Details DOI

JBHI Journal 2026 Journal Article

GCL-MSE: Graph Contrastive Learning with Mutual Similarity Enhancement for Drug Repositioning

Shasha Tao
Jin Liu
Min Xiang
Xin Ma
Tongtong Huo
Xiaolin Ning

Amidst the shift to data-driven drug repositioning, existing models struggle to capture complex semantic and topological relationships in biomedical knowledge graphs for drug-disease association (DDA) mining. We propose a Graph Contrastive Learning with Mutual Similarity Enhancement (GCL-MSE). The core innovation lies in defining a concept of mutual similarity. This concept comprises two aspects: drug therapeutic domain similarity, which captures the functional associations between drugs based on their therapeutic spectra, and disease pharmacological response similarity, which reflects the pathological associations between diseases based on drug response patterns. Based on this concept, a Mutual Similarity Enhancement mechanism (MSE) is constructed to fuse four similarities, to build a semantic relationship topology that captures the complex semantic dependencies in DDA. Further, an Adaptive Orthogonal Noise Contrastive Estimation Loss (AdaOrthoNCE) is proposed to disentangle biological relationships in the latent space while optimizing discriminative representations. GCL MSE integrates the semantic topology via MSE, employs a three-channel graph convolutional model to generate topology-semantic co-representations, and utilizes AdaOrthoNCE to learn optimized embeddings, ultimately enabling cross-scale DDA prediction. Experimental results demonstrate that GCL-MSE significantly outperforms state of-the-art models in both AUROC and AUPRC metrics, with improvements of over 4. 8% in AUROC and 25. 5% in AUPRC, thereby validating the effectiveness of collaborative modeling that integrates features from pharmacological, therapeutic, and topological perspectives. Additionally, GCL MSE predicts the therapeutic roles of drugs such as lamotrigine for Alzheimer's disease and hydroxyurea for breast cancer. Molecular docking experiments and related studies further confirm its validity.

AAAI Conference 2026 Conference Paper

Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation

Ziyang Huang
Jiagang Chen
Jin Liu
Shunping Ji

3D Gaussian Splatting (3DGS) has emerged as a leading framework for novel view synthesis, yet its core optimization challenges remain underexplored. We identify two key issues in 3DGS optimization: entrapment in suboptimal local optima and insufficient convergence quality. To address these, we propose Opt3DGS, a robust framework that enhances 3DGS through a two-stage optimization process of adaptive exploration and curvature-guided exploitation. In the exploration phase, an Adaptive Weighted Stochastic Gradient Langevin Dynamics (SGLD) method enhances global search to escape local optima. In the exploitation phase, a Local Quasi-Newton Direction-guided Adam optimizer leverages curvature information for precise and efficient convergence. Extensive experiments on diverse benchmark datasets demonstrate that Opt3DGS achieves state-of-the-art rendering quality by refining the 3DGS optimization process without modifying its underlying representation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Wavefront-Constrained Passive Obscured Object Detection

Zhiwen Zheng
Yiwei Ouyang
Zhao Huang
Tao Zhang
Xiaoshuai Zhang
Huiyu Zhou
Wenwen Tang
Shaowei Jiang

Accurately localizing and segmenting obscured objects from faint light patterns beyond the field of view is highly challenging due to multiple scattering and medium-induced perturbations. Most existing methods, based on real-valued modeling or local convolutional operations, are inadequate for capturing the underlying physics of coherent light propagation. Moreover, under low signal-to-noise conditions, these methods often converge to non-physical solutions, severely compromising the stability and reliability of the observation. To address these challenges, we propose a novel physics-driven Wavefront Propagating Compensation Network (WavePCNet) to simulate wavefront propagation and enhance the perception of obscured objects. This WavePCNet integrates the Tri-Phase Wavefront Complex-Propagation Reprojection (TriWCP) to incorporate complex amplitude transfer operators to precisely constrain coherent propagation behavior, along with a momentum memory mechanism to effectively suppress the accumulation of perturbations. Additionally, a High-frequency Cross-layer Compensation Enhancement is introduced to construct frequency-selective pathways with multi-scale receptive fields and dynamically models structural consistency across layers, further boosting the model’s robustness and interpretability under complex environmental conditions. Extensive experiments conducted on four physically collected datasets demonstrate that WavePCNet consistently outperforms state-of-the-art methods across both accuracy and robustness.

PDF Details DOI

JBHI Journal 2026 Journal Article

WOADNet: A Wavelet-Inspired Orientational Adaptive Dictionary Network for CT Metal Artifact Reduction

Tong Jin
Jin Liu
Diandian Wang
Kun Wang
Chenlong Miao
Yikun Zhang
Dianlin Hu
Zhan Wu

In computed tomography (CT), metal artifacts pose a persistent challenge to achieving high-quality imaging. Despite advancements in metal artifact reduction (MAR) techniques, many existing approaches have not fully leveraged the intrinsic a priori knowledge related to metal artifacts, improved model interpretability, or addressed the complex texture of CT images effectively. To address these limitations, we propose a novel and interpretable framework, the wavelet-inspired oriented adaptive dictionary network (WOADNet). WOADNet builds on sparse coding with orientational information in the wavelet domain. By exploring the discriminative features of artifacts and anatomical tissues, we adopt a high-precision filter parameterization strategy that incorporates multiangle rotations. Furthermore, we integrate a reweighted sparse constraint framework into the convolutional dictionary learning process and employ a cross-space, multiscale attention mechanism to construct an adaptive convolutional dictionary unit for the artifact feature encoder. This innovative design allows for flexible adjustment of weights and convolutional representations, resulting in significant image quality improvements. The experimental results using synthetic and clinical datasets demonstrate that WOADNet outperforms both traditional and state-of-the-art MAR methods in terms of suppressing artifacts.

IJCAI Conference 2025 Conference Paper

A Survey on the Feedback Mechanism of LLM-based AI Agents

Zhipeng Liu
Xuefeng Bai
Kehai Chen
Xinyang Chen
Xiucheng Li
Yang Xiang
Jin Liu
Hong-Dong Li

Large language models (LLMs) are increasingly being adopted to develop general-purpose AI agents. However, it remains challenging for these LLM-based AI agents to efficiently learn from feedback and iteratively optimize their strategies. To address this challenge, tremendous efforts have been dedicated to designing diverse feedback mechanisms for LLM-based AI agents. To provide a comprehensive overview of this rapidly evolving field, this paper presents a systematic review of these studies, offering a holistic perspective on the feedback mechanisms in LLM-based AI agents. We begin by discussing the construction of LLM-based AI agents, introducing a generalized framework that encapsulates much of the existing work. Next, we delve into the exploration of feedback mechanisms, categorizing them into four distinct types: internal feedback, external feedback, multi-agent feedback, and human feedback. Additionally, we provide an overview of evaluation protocols and benchmarks specifically tailored for LLM-based AI agents. Finally, we highlight the significant challenges and identify potential directions for future studies. The relevant papers are summarized and will be consistently updated at https: //github. com/kevinson7515/Agents-Feedback-Mechanisms.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Altered brain network dynamics during rumination in remitted depression

Su Shu
Wenwen Ou
Mohan Ma
Hairuo He
Qianqian Zhang
Mei Huang
Wentao Chen
Aoqian Deng

Rumination is a known risk factor for depression relapse. Understanding its neurobiological mechanisms during depression remission can inform strategies to prevent relapse, yet the temporal dynamics of brain networks during rumination in remitted depression remain unclear. Here, we collected rumination induction fMRI data from 42 patients with remitted depression and 41 healthy controls (HCs). Using an energy landscape approach, we investigated the temporal dynamics of brain networks during rumination. The appearance frequency (AF) and transition frequency (TF) metrics were defined to quantify the dynamic properties of brain states. Patients during remission showed higher levels of rumination than HCs. Both groups exhibited four brain states during rumination, which consisted of complementary network group activation (states 1 and 2, states 3 and 4). In patients, the AFs of and reciprocal TFs between states 1 and 2 during rumination were significantly increased, while AFs of states 3 and 4 and reciprocal TFs involving states 1-3, 1-4, 2-3, and 2-4 were decreased, both when compared to HCs and relative to patients themselves during distraction. Moreover, we found that for patients, the AF of state 1 was negatively correlated with rumination levels and marginally positively associated with attention, while the AF of state 2 was negatively associated with performance on attention tasks. Our study revealed altered dynamic characteristics of brain states composed of network groups during rumination in remitted depression. Additionally, the findings suggest that heightened self-focus linked to rumination may impair the brain's ability to efficiently allocate attentional resources.

JBHI Journal 2025 Journal Article

An Autonomous AI Framework for Knee Osteoarthritis Diagnosis via Semi-Supervised Learning and Dual Knowledge Distillation

Li Peng
Li Xu
Xiaoding Wang
Lizhao Wu
Jin Liu
Weiquan Zeng
Md. Jalil Piran

In the diagnosis of knee osteoarthritis, imaging analysis relies on accurate classification models to assess the severity of the disease. Traditional methods often require large amounts of labeled data, which is challenging in many developing countries, especially in resource-limited areas where the scarcity of labeled data becomes a bottleneck due to a lack of medical resources and qualified annotators. Privacy concerns also arise when using high-quality datasets from developed countries. This paper proposes a semi-supervised dual-knowledge distillation framework, PADistillation, that leverages autonomous AI to expand the reach of telemedicine and remote diagnostics while addressing data scarcity and privacy problems. To overcome the challenge of insufficient labeled data, the framework uses attention-guided distillation, employing high-attention pixels and channels to guide the student model's learning, thereby enhancing classification performance with limited labeled data. To ensure patient privacy during training, a personalized pixel shuffling method is proposed, dynamically determining the privacy protection priority of different regions by measuring the visual disorder of image areas. Through autonomous optimization and real-time decision making, PADistillation operates efficiently in resourceconstrained environments and supports telemedicine and remote diagnostic needs. Even with limited labeled data, the experimental results show that PADistillation achieves an accuracy rate of 88. 19%, a precision rate of 86. 28%, and an F1 score of 86. 94%. Compared with the mainstream semi-supervised methods, its accuracy rate is increased by more than 2%, the training efficiency is improved by 30%, and the privacy protection mechanism only leads to a performance loss of 1. 2%.

YNICL Journal 2025 Journal Article

Brain network dynamics during rumination relate to relapse of depression

Su Shu
Yumeng Ju
Mi Wang
Wenwen Ou
Mohan Ma
Qianqian Zhang
Mei Huang
Hairuo He

BACKGROUND: Rumination is a maladaptive cognitive style and a risk factor for relapse of depression. However, the clinically relevant pattern of dynamic network reconfiguration during rumination in remitted depression and its implication in relapse remained unclear. METHODS: We employed a rumination induction neuroimaging paradigm in which subjects would be guided into an active rumination state and a distraction state. Forty-two patients with remitted depression were involved. Participants underwent assessments of rumination behavior and imaging tasks, and were then monitored for two year to assess the potential relapse of depression. A time-resolved community detection approach was applied to investigate the temporal dynamics of brain networks, and the dynamic network properties including flexibility and integration were analyzed. RESULTS: = 0.036). Moreover, elastic net regression indicated that dynamic network features could predict two-year relapse outcomes with moderate accuracy (AUC = 0.70). CONCLUSIONS: Our findings reveal a potential mechanistic link between the brain network dynamics during rumination and relapse of depression, shedding light on the intricate relationship between cognitive-affective processes, neural dynamics, and the potential vulnerability to depression recurrence.

JBHI Journal 2025 Journal Article

CA 2 CL: Cluster-Aware Adversarial Contrastive Learning for Pathological Image Analysis

Junjian Li
Hulin Kuang
Jin Liu
Hailin Yue
Jianxin Wang

Pathological diagnosis assists in saving human lives, but such models are annotation hungry and pathological images are notably expensive to annotate. Contrastive learning could be a promising solution that relies only on the unlabeled training data to generate informative representations. However, the majority of current methods in contrastive learning have the following two issues: (1) positive samples produced through random augmentation are less challenging, and (2) false negative pairs problem caused by negative sampling bias. To alleviate the above issues, we propose a novel contrastive learning method called Cluster-Aware Adversarial Contrastive Learning (CA 2 CL). Specifically, a mixed data augmentation technique is provided to learn more transferable representations by generating more discriminative sample pairs. Furthermore, to mitigate the effects of inherent false negative pairs, we adopt a cluster-aware loss to identify similarities between instances and incorporate them into the process of contrastive learning. Finally, we generate challenging contrastive data pairs by adversarial learning, and adversarially learn robust representations in the representation space without the labeled training data, which aims to maximize the similarity between the augmented sample and the related adversarial sample. Our proposed CA 2 CL is evaluated on two public datasets: NCT-CRC-HE and PCam for the fine-tuning and linear evaluation tasks and on two other public datasets: GlaS and CARG for the detection and segmentation tasks, respectively. Extensive experimental results demonstrate the superior performance improvement of our method over several Self-supervised learning (SSL) methods and ImageNet pretraining particularly in scenarios with limited data availability for all four tasks.

ICML Conference 2025 Conference Paper

Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction

Yinfeng Chen
Jin Liu
Rui Qiu

The normal vectors obtained from the support vector machine (SVM) method offer the potential to achieve sufficient dimension reduction in both classification and regression scenarios. Motivated by it, we in this paper introduce a unified framework for nonlinear sufficient dimension reduction based on classification ensemble. Kernel principal SVM, which leverages the reproducing kernel Hilbert space, can almost be regarded as a special case of this framework, and we generalize it by using a neural network function class for more flexible deep nonlinear reduction. We theoretically prove its unbiasedness with respect to the central $\sigma$-field and provide a nonasymptotic upper bound for the estimation error. Simulations and real data analysis demonstrate the considerable competitiveness of the proposed method, especially under heavy data contamination, large sample sizes, and complex inputs.

ICML Conference 2025 Conference Paper

Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging

Junkang Liu
Yuanyuan Liu 0001
Fanhua Shang
Hongying Liu 0001
Jin Liu
Wei Feng 0005

For federated learning (FL) algorithms such as FedSAM, their generalization capability is crucial for real-word applications. In this paper, we revisit the generalization problem in FL and investigate the impact of data heterogeneity on FL generalization. We find that FedSAM usually performs worse than FedAvg in the case of highly heterogeneous data, and thus propose a novel and effective federated learning algorithm with Stochastic Weight Averaging (called FedSWA), which aims to find flatter minima in the setting of highly heterogeneous data. Moreover, we introduce a new momentum-based stochastic controlled weight averaging FL algorithm (FedMoSWA), which is designed to better align local and global models. Theoretically, we provide both convergence analysis and generalization bounds for FedSWA and FedMoSWA. We also prove that the optimization and generalization errors of FedMoSWA are smaller than those of their counterparts, including FedSAM and its variants. Empirically, experimental results on CIFAR10/100 and Tiny ImageNet demonstrate the superiority of the proposed algorithms compared to their counterparts.

EAAI Journal 2025 Journal Article

Modeling temporal continuity of spatial interactions for vessel trajectories prediction in maritime transportation systems

Xiliang Zhang
Jin Liu
Chengcheng Chen
Peizhu Gong
Zhongdai Wu
Lei Guo

Learning the intricate spatio-temporal interactions among vessels poses a fundamental challenge to vessel trajectory prediction (VTP). Prevailing graph neural network-based methods typically employ a three-stage independent architecture, modeling spatial and temporal dependencies separately, which not only overlooks the temporal continuity of spatial interactions but also introduces higher computational overhead. Moreover, considering interaction semantics at distinct moments equally during the modeling process may restrict the effective learning for certain key features. To address these issues, our paper proposes an innovative Heterogeneous Spatio-temporal Graph Neural Network (HSTGN) that employs hierarchical aggregations, encompassing vessel node-level, temporal edge-level, and self-attention-level aggregations, tailored for VTP. Specifically, a heterogeneous graph is first constructed through the transformation of node and edge generators, allowing vessels to interact freely with each other across temporal dimensions. A key innovation is the vessel multi-relational graph aggregation module (VMGA), which selectively aggregates edge-specific semantics and assigns adaptive weights to enhance interaction modeling. Furthermore, we devise a gated temporal convolution module (GTCN) to compensate for potential global dependencies that VMGA might not capture. Finally, HSTGN integrates VMGA and GTCN in parallel to refine spatio-temporal correlations for more precise prediction. This study enhances VTP accuracy and efficiency, enabling safer navigation and optimized maritime route planning. Extensive experiments on three real-world Automatic Identification System (AIS) datasets demonstrate that HSTGN outperforms state-of-the-art approaches, achieving a 9. 47% improvement in mean absolute error (MAE), 1. 43% in root-mean-square error (RMSE), 2. 72% in mean absolute percentage error (MAPE), and a 43. 06% increase in inference speed, while utilizing fewer model parameters.

EAAI Journal 2025 Journal Article

Multilingual entity alignment by abductive knowledge reasoning on multiple knowledge graphs

Muhammad Usman Akhtar
Jin Liu
Zhiwen Xie
Xiaohui Cui
Xiao Liu
Bo Huang

Objectives: Entity alignment (EA) seeks to identify similar real-world objects in different multilingual knowledge graphs (KGs), also known as ontology alignment. EA assists in handling a wide range of language semantics and in building integrated knowledge bases. However, most mainstream studies have focused on structural information, paying little attention to insufficient contextual information and limited handling of complex relationships. This paper aims to address these limitations and improve EA performance and efficiency. Methods: This paper investigates multilingual EA techniques and proposes a novel Abductive Knowledge Reasoning (AKR) model to address these issues. AKR can compute complex relationship semantics context by reasoning and enrich counterpart entity contextual information through centrality calculation, which helps connect distant entities in multilingual KGs. Novelty: The proposed AKR model introduces a new approach to EA by integrating centrality calculation and relational semantics reasoning. This method overcomes the limitations of existing EA techniques by effectively handling insufficient contextual information and complex relationships in multilingual KGs. Findings: AKR outperforms all state-of-the-art EA models across five datasets. AKR achieves H i t @ 1 score of 79. 4%, for entity alignment between Chinese-to-English knowledge graphs representing 19. 9% improvement over the best-performing translation-based model, Neighborhood-Aware Attentional Representation Entity Alignment, and a 5. 0% improvement over the best-performing graph neural network-based model, Relational Semantics Augmentation.

IJCAI Conference 2025 Conference Paper

OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models

Xiaomeng Fu
Xi Wang
Qiao Li
Jin Liu
Jiao Dai
Jizhong Han
Xingyu Gao

The data-intensive nature of Diffusion models amplifies the risks of privacy infringements and copyright disputes, particularly when training on extensive unauthorized data scraped from the Internet. Membership Inference Attacks (MIA) aim to determine whether a data sample has been utilized by the target model during training, thereby serving as a pivotal tool for privacy preservation. Current MIA employs the prediction loss to distinguish between training member samples and non-members. These methods assume that, compared to non-members, members, having been encountered by the model during training result in a smaller prediction loss. However, this assumption proves ineffective in diffusion models due to the random noise sampled during the training process. Rather than estimating the loss, our approach examines this random noise and reformulate the MIA as a noise search problem, assuming that members are more feasible to find the noise used in the training process. We formulate this noise search process as an optimization problem and employ the fixed-point iteration to solve it. We analyze current MIA methods through the lens of the noise search framework and reveal that they rely on the first residual as the discriminative metric to differentiate members and non-members. Inspired by this observation, we introduce OMS, which augments existing MIA methods by iterating One More fixed-point Step to include a further residual, i. e. , the second residual. We integrate our method into various MIA methods across different diffusion models. The experimental results validate the efficacy of our proposed approach.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Rank labels scaffold social cognitive maps in the hippocampal-entorhinal system

Jin Liu
Yanfei Zhou
Hongzhi Wang
Li-Zhuang Yang
Hai Li

How do humans construct mental representations of social hierarchies in the absence of direct interpersonal interactions? In many real-world contexts, humans rely on symbolic rank labels-such as titles or performance ratings-to navigate social hierarchies, yet how these abstract labels shape neural representations of social structure remains unclear. Using fMRI, we investigated whether learning face-rank associations along two orthogonal social dimensions-competence and morality-engages spatial coding mechanisms within the hippocampal-entorhinal system. Twenty-four participants completed an extensive three-day protocol-including baseline trait evaluation (Day 1), extensive behavioral training (Day 2), and multidimensional decision-making and spatial reconstruction tasks (Day 3). Behavioral results support that larger rank distances produced faster and more accurate hiring decisions, indicating reliance on an internal spatial map. Subsequent representational-similarity analysis further revealed that the hippocampus encoded Euclidean distances between individuals, whereas the entorhinal cortex expressed a hexadirectional grid-like pattern that aligned with the inferred directions of social relationships. These converging behavioral and neural results demonstrate that explicit symbolic ranks rapidly scaffold a two-dimensional cognitive map of social hierarchy, repurposing spatial-navigation mechanisms for abstract social reasoning. This insight advances social-cognitive neuroscience and highlights principles that could inform artificial-intelligence systems designed for hierarchical reasoning and decision-making in complex social environments.

IJCAI Conference 2025 Conference Paper

Stability and Generalization for Stochastic (Compositional) Optimizations

Xiaokang Pan
Jin Liu
Hulin Kuang
Youqi Li
Lixing Chen
Zhe Qu

The use of estimators instead of stochastic gradients for updates has been shown to improve algorithm convergence rates of, but their impact on generalization remains under-explored. In this paper, we investigate how estimators influence generalization. Our focus is on two widely studied problems: stochastic optimization (SO) and stochastic compositional optimization (SCO), both under convex and non-convex settings. For SO problems, we first analyze the generalization error of the STORM algorithm as a foundational step. We then extend our analysis to SCO problems by introducing an algorithmic framework that encompasses several popular algorithmic approaches. Through this framework, we conduct a generalization analysis, uncovering new insights into the impact of estimators on generalization. Subsequently, we provide a detailed analysis of three specific algorithms within this framework: SCGD, SCSC, and COVER, to explore the effects of different estimator strategies. Furthermore, in the context of SCO, we propose a novel definition of stability and a new decomposition of excess risk in the non-convex setting. Our analysis indicates two key findings: (1) In SCO problems, eliminating the estimator for the gradient of the inner function does not impact generalization performance while significantly reducing computational and storage overhead. (2) Faster convergence rates are consistently associated with better generalization performance.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation

Xingru Huang
Jian Huang
Yihao Guo
Tianyun Zhang
Zhao Huang
Yaqi Wang
Ruipu Tang
Guangliang Cheng

Information retrieved from three dimensions is treated uniformly in CNN-based volumetric segmentation methods. However, such neglect of axial disparities fails to capture true spatio-temporal variations. This paper introduces the volumetric axial disentanglement to address the disparities in spatial information along different axial dimensions. Building on this concept, we propose the Post-Axial Refiner (PaR) module to refine segmentation masks by implementing axial disentanglement on the specific axis of the volumetric medical sequences. As a plug-and-play enhancement to existing volumetric segmentation architecture, PaR further utilizes specialized attention approaches to learn disentangled post-decoding features, enhancing spatial representation and structural detail. Validation on various datasets demonstrates PaR's consistent elevation of segmentation precision and boundary clarity across 11 baselines and different imaging modalities, achieving state-of-the-art performance on multiple datasets. Experimental tests demonstrate the ability of volumetric axial disentanglement to refine the segmentation of volumetric medical images. Code is released at https: //github. com/IMOP-lab/PaR-Pytorch.

PDF Details DOI

EAAI Journal 2024 Journal Article

A multi-task learning model for recommendation based on fusion of dynamic and static neighbors

Bo Huang
Sirui Zheng
Hamido Fujita
Jin Liu

To improve recommendation performance, this study introduces self-supervised learning into recommendation systems and proposes a multi-task learning recommendation framework that combines static neighbor and dynamic neighbor contrastive learning. Specifically, this study considers node relationships at both the graph and embedding levels, which can be defined in two aspects: (1) Static neighbors, which are positive nodes obtained by integrating information from user-item interaction graphs and social graphs. (2) Dynamic neighbors refer to nodes at the encoding level that are similar, but not necessarily the same, at each iteration; hence, they are termed dynamic neighbors. By employing static neighbor contrastive learning and dynamic neighbor contrastive learning as auxiliary tasks for the main recommendation task, we optimized the user and item embeddings. Through extensive experiments using multiple real datasets, we validate the effectiveness of the proposed approach and its components.

ICLR Conference 2024 Conference Paper

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit

Duanyi Yao
Songze Li
Ye Xue
Jin Liu

Vertical federated learning (VFL), where each participating client holds a subset of data features, has found numerous applications in finance, healthcare, and IoT systems. However, adversarial attacks, particularly through the injection of adversarial examples (AEs), pose serious challenges to the security of VFL models. In this paper, we investigate such vulnerabilities through developing a novel attack to disrupt the VFL inference process, under a practical scenario where the adversary is able to *adaptively corrupt a subset of clients*. We formulate the problem of finding optimal attack strategies as an online optimization problem, which is decomposed into an inner problem of adversarial example generation (AEG) and an outer problem of corruption pattern selection (CPS). Specifically, we establish the equivalence between the formulated CPS problem and a multi-armed bandit (MAB) problem, and propose the Thompson sampling with Empirical maximum reward (E-TS) algorithm for the adversary to efficiently identify the optimal subset of clients for corruption. The key idea of E-TS is to introduce an estimation of the expected maximum reward for each arm, which helps to specify a small set of *competitive arms*, on which the exploration for the optimal arm is performed. This significantly reduces the exploration space, which otherwise can quickly become prohibitively large as the number of clients increases. We analytically characterize the regret bound of E-TS, and empirically demonstrate its capability of efficiently revealing the optimal corruption pattern with the highest attack success rate, under various datasets of popular VFL tasks.

AAAI Conference 2024 Conference Paper

Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization

Jin Liu
Xiaokang Pan
Junwen Duan
Hong-Dong Li
Youqi Li
Zhe Qu

This paper delves into the realm of stochastic optimization for compositional minimax optimization—a pivotal challenge across various machine learning domains, including deep AUC and reinforcement learning policy evaluation. Despite its significance, the problem of compositional minimax optimization is still under-explored. Adding to the complexity, current methods of compositional minimax optimization are plagued by sub-optimal complexities or heavy reliance on sizable batch sizes. To respond to these constraints, this paper introduces a novel method, called Nested STOchastic Recursive Momentum (NSTORM), which can achieve the optimal sample complexity and obtain the nearly accuracy solution, matching the existing minimax methods. We also demonstrate that NSTORM can achieve the same sample complexity under the Polyak-Lojasiewicz (PL)-condition—an insightful extension of its capabilities. Yet, NSTORM encounters an issue with its requirement for low learning rates, potentially constraining its real-world applicability in machine learning. To overcome this hurdle, we present ADAptive NSTORM (ADA-NSTORM) with adaptive learning rates. We demonstrate that ADA-NSTORM can achieve the same sample complexity but the experimental results show its more effectiveness. All the proposed complexities indicate that our proposed methods can match lower bounds to existing minimax optimizations, without requiring a large batch size in each iteration. Extensive experiments support the efficiency of our proposed methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation

Hongbo Wang
Jie Cao
Jin Liu
Xiaoqiang Zhou
Huaibo Huang
Ran He

Recent advancements in 3D content generation have been significant, primarily due to the visual priors provided by pretrained diffusion models. However, large 2D visual models exhibit spatial perception hallucinations, leading to multi-view inconsistency in 3D content generated through Score Distillation Sampling (SDS). This phenomenon, characterized by overfitting to specific views, is referred to as the "Janus Problem". In this work, we investigate the hallucination issues of pretrained models and find that large multimodal models without geometric constraints possess the capability to infer geometric structures, which can be utilized to mitigate multi-view inconsistency. Building on this, we propose a novel tuning-free method. We represent the multimodal inconsistency query information to detect specific hallucinations in 3D content, using this as an enhanced prompt to re-consist the 2D renderings of 3D and jointly optimize the structure and appearance across different views. Our approach does not require 3D training data and can be implemented plug-and-play within existing frameworks. Extensive experiments demonstrate that our method significantly improves the consistency of 3D content generation and specifically mitigates hallucinations caused by pretrained large models, achieving state-of-the-art performance compared to other optimization methods.

PDF Details DOI

JMLR Journal 2024 Journal Article

Inference on High-dimensional Single-index Models with Streaming Data

Dongxiao Han
Jinhan Xie
Jin Liu
Liuquan Sun
Jian Huang
Bei Jiang
Linglong Kong

Traditional statistical methods are faced with new challenges due to streaming data. The major challenge is the rapidly growing volume and velocity of data, which makes storing such huge data sets in memory impossible. The paper presents an online inference framework for regression parameters in high-dimensional semiparametric single-index models with unknown link functions. The proposed online procedure updates only the current data batch and summary statistics of historical data instead of re-accessing the entire raw data set. At the same time, we do not need to estimate the unknown link function, which is a highly challenging task. In addition, a generalized convex loss function is used in the proposed inference procedure. To illustrate the proposed method, we use the Huber loss function and the negative log-likelihood of the logistic regression model. In this study, the asymptotic normality of the proposed online debiased Lasso estimators and the bounds of the proposed online Lasso estimators are investigated. To evaluate the performance of the proposed method, extensive simulation studies have been conducted. We provide applications to Nasdaq stock prices and financial distress data sets. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

AAAI Conference 2024 Conference Paper

Region-Aware Exposure Consistency Network for Mixed Exposure Correction

Jin Liu
Huiyuan Fu
Chuanming Wang
Huadong Ma

Exposure correction aims to enhance images suffering from improper exposure to achieve satisfactory visual effects. Despite recent progress, existing methods generally mitigate either overexposure or underexposure in input images, and they still struggle to handle images with mixed exposure, i.e., one image incorporates both overexposed and underexposed regions. The mixed exposure distribution is non-uniform and leads to varying representation, which makes it challenging to address in a unified process. In this paper, we introduce an effective Region-aware Exposure Correction Network (RECNet) that can handle mixed exposure by adaptively learning and bridging different regional exposure representations. Specifically, to address the challenge posed by mixed exposure disparities, we develop a region-aware de-exposure module that effectively translates regional features of mixed exposure scenarios into an exposure-invariant feature space. Simultaneously, as de-exposure operation inevitably reduces discriminative information, we introduce a mixed-scale restoration unit that integrates exposure-invariant features and unprocessed features to recover local information. To further achieve a uniform exposure distribution in the global image, we propose an exposure contrastive regularization strategy under the constraints of intra-regional exposure consistency and inter-regional exposure continuity. Extensive experiments are conducted on various datasets, and the experimental results demonstrate the superiority and generalization of our proposed method. The code is released at: https://github.com/kravrolens/RECNet.

PDF Details DOI

ICML Conference 2024 Conference Paper

Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to K-Level Stochastic Optimizations

Xiaokang Pan
Xingyu Li
Jin Liu
Tao Sun
Kai Sun
Lixing Chen
Zhe Qu

STOchastic Recursive Momentum (STORM)-based algorithms have been widely developed to solve one to $K$-level ($K \geq 3$) stochastic optimization problems. Specifically, they use estimators to mitigate the biased gradient issue and achieve near-optimal convergence results. However, there is relatively little work on understanding their generalization performance, particularly evident during the transition from one to $K$-level optimization contexts. This paper provides a comprehensive generalization analysis of three representative STORM-based algorithms: STORM, COVER, and SVMR, for one, two, and $K$-level stochastic optimizations under both convex and strongly convex settings based on algorithmic stability. Firstly, we define stability for $K$-level optimizations and link it to generalization. Then, we detail the stability results for three prominent STORM-based algorithms. Finally, we derive their excess risk bounds by balancing stability results with optimization errors. Our theoretical results provide strong evidence to complete STORM-based algorithms: (1) Each estimator may decrease their stability due to variance with its estimation target. (2) Every additional level might escalate the generalization error, influenced by the stability and the variance between its cumulative stochastic gradient and the true gradient. (3) Increasing the batch size for the initial computation of estimators presents a favorable trade-off, enhancing the generalization performance.

JBHI Journal 2023 Journal Article

BEA-Net: Body and Edge Aware Network With Multi-Scale Short-Term Concatenation for Medical Image Segmentation

Hulin Kuang
Yahui Wang
Yixiong Liang
Jin Liu
Jianxin Wang

Medical image segmentation is indispensable for diagnosis and prognosis of many diseases. To improve the segmentation performance, this study proposes a new 2D body and edge aware network with multi-scale short-term concatenation for medical image segmentation. Multi-scale short-term concatenation modules which concatenate successive convolution layers with different receptive fields, are proposed for capturing multi-scale representations with fewer parameters. Body generation modules with feature adjustment based on weight map computing via enlarging the receptive fields, and edge generation modules with multi-scale convolutions using Sobel kernels for edge detection, are proposed to separately learn body and edge features from convolutional features in decoders, making the proposed network be body and edge aware. Based on the body and edge modules, we design parallel body and edge decoders whose outputs are fused to achieve the final segmentation. Besides, deep supervision from the body and edge decoders is applied to ensure the effectiveness of the generated body and edge features and further improve the final segmentation. The proposed method is trained and evaluated on six public medical image segmentation datasets to show its effectiveness and generality. Experimental results show that the proposed method achieves better average Dice similarity coefficient and 95% Hausdorff distance than several benchmarks on all used datasets. Ablation studies validate the effectiveness of the proposed multi-scale representation learning modules, body and edge generation modules and deep supervision.

JBHI Journal 2023 Journal Article

DREAM-Net: Deep Residual Error Iterative Minimization Network for Sparse-View CT Reconstruction

Yikun Zhang
Dianlin Hu
Shilei Hao
Jin Liu
Guotao Quan
Yi Zhang
Xu Ji
Yang Chen

Sparse-view Computed Tomography (CT) has the ability to reduce radiation dose and shorten the scan time, while the severe streak artifacts will compromise anatomical information. How to reconstruct high-quality images from sparsely sampled projections is a challenging ill-posed problem. In this context, we propose the unrolled Deep Residual Error iterAtive Minimization Network (DREAM-Net) based on a novel iterative reconstruction framework to synergize the merits of deep learning and iterative reconstruction. DREAM-Net performs constraints using deep neural networks in the projection domain, residual space, and image domain simultaneously, which is different from the routine practice in deep iterative reconstruction frameworks. First, a projection inpainting module completes the missing views to fully explore the latent relationship between projection data and reconstructed images. Then, the residual awareness module attempts to estimate the accurate residual image after transforming the projection error into the image space. Finally, the image refinement module learns a non-standard regularizer to further fine-tune the intermediate image. There is no need to empirically adjust the weights of different terms in DREAM-Net because the hyper-parameters are embedded implicitly in network modules. Qualitative and quantitative results have demonstrated the promising performance of DREAM-Net in artifact removal and structural fidelity.

ICML Conference 2023 Conference Paper

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

Songze Li
Duanyi Yao
Jin Liu

In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features are privately stored on different clients. The problem of split VFL is to train a model split between the server and the clients. This paper aims to address two major challenges in split VFL: 1) performance degradation due to straggling clients during training; and 2) data and model privacy leakage from clients’ uploaded data embeddings. We propose FedVS to simultaneously address these two challenges. The key idea of FedVS is to design secret sharing schemes for the local data and models, such that information-theoretical privacy against colluding clients and curious server is guaranteed, and the aggregation of all clients’ embeddings is reconstructed losslessly, via decrypting computation shares from the non-straggling clients. Extensive experiments on various types of VFL datasets (including tabular, CV, and multi-view) demonstrate the universal advantages of FedVS in straggler mitigation and privacy protection over baseline protocols.

EAAI Journal 2023 Journal Article

VIKOR method for Pythagorean hesitant fuzzy multi-attribute decision-making based on regret theory

Nian Zhang
Yifan Zhou
Jin Liu
Guiwu Wei

In reality, influenced by fuzzy information and irrational behavior, decision-makers are typically difficult to make decisions. Therefore, how to comprehensively express the evaluation information and accurately quantify the psychological behavior becomes a primary key to improve the efficiency of decision-making. Aiming at multi-attribute decision-making problem with completely unknown weight information and Pythagorean hesitate fuzzy evaluation value, a VIKOR method based on regret theory is proposed. Firstly, the weights are determined from two levels of alternative and attribute. Secondly, the relative closeness decision matrix is constructed by TOPSIS method. Then, the VIKOR method is used to calculate the values of group utility and individual regret based on regret perception value, which can describe the ranking of alternatives. Finally, the availability and effectiveness of this method are proved by sensitivity and comparative analysis. In conclusion, the proposed method not only considers the compromise preference under Pythagorean hesitant fuzzy environment, but also takes into account regret psychologic behavior of decision-makers.

JBHI Journal 2022 Journal Article

Multimodal Disentangled Variational Autoencoder With Game Theoretic Interpretability for Glioma Grading

Jianhong Cheng
Min Gao
Jin Liu
Hailin Yue
Hulin Kuang
Jun Liu
Jianxin Wang

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterwards, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC: 0. 9939) on a public dataset, and good generalization performance (AUC: 0. 9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes.

JBHI Journal 2022 Journal Article

PRIOR: Prior-Regularized Iterative Optimization Reconstruction For 4D CBCT

Dianlin Hu
Yikun Zhang
Jin Liu
Yi Zhang
Jean Louis Coatrieux
Yang Chen

4D cone-beam computed tomography (CBCT) is an important imaging modality in image-guided radiation therapy to address the motion-induced artifacts caused by organ movements during the respiratory process. However, due to the extremely sparse projection data for each temporal phase, 4D CBCT reconstructions will suffer from severe streaking artifacts. Therefore, to tackle the streak artifacts and provide high-quality images, we proposed a framework termed Prior-Regularized Iterative Optimization Reconstruction (PRIOR) for 4D CBCT. The PRIOR framework combines the physics-based model and data-driven method simultaneously, with powerful feature extracting capacity, significantly promoting the image quality compared to single model-based or deep learning-based methods. Besides, we designed a specialized deep learning model named PRIOR-Net, which can effectively excavate the static information in the prior image reconstructed from the fully-sampled projections at the encoding stage to improve the reconstruction performance for individual phase-resolved images. Both the simulated and clinical 4D CBCT datasets were performed to evaluate the performance of the PRIOR-Net and the PRIOR framework. Compared with the advanced 4D CBCT reconstruction methods, the proposed methods achieve promising results quantitatively and qualitatively in streak artifact suppression, soft tissue restoration, and tiny detail preservation.

YNIMG Journal 2022 Journal Article

Structural insight into the individual variability architecture of the functional brain connectome

Lianglong Sun
Xinyuan Liang
Dingna Duan
Jin Liu
Yuhan Chen
Xindi Wang
Xuhong Liao
Mingrui Xia

Human cognition and behaviors depend upon the brain's functional connectomes, which vary remarkably across individuals. However, whether and how the functional connectome individual variability architecture is structurally constrained remains largely unknown. Using tractography- and morphometry-based network models, we observed the spatial convergence of structural and functional connectome individual variability, with higher variability in heteromodal association regions and lower variability in primary regions. We demonstrated that functional variability is significantly predicted by a unifying structural variability pattern and that this prediction follows a primary-to-heteromodal hierarchical axis, with higher accuracy in primary regions and lower accuracy in heteromodal regions. We further decomposed group-level connectome variability patterns into individual unique contributions and uncovered the structural-functional correspondence that is associated with individual cognitive traits. These results advance our understanding of the structural basis of individual functional variability and suggest the importance of integrating multimodal connectome signatures for individual differences in cognition and behaviors.

AIIM Journal 2021 Journal Article

DeepMI: Deep multi-lead ECG fusion for identifying myocardial infarction and its occurrence-time

Girmaw Abebe Tadesse
Hamza Javed
Komminist Weldemariam
Yong Liu
Jin Liu
Jiyan Chen
Tingting Zhu

Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independently of one another. We propose an end-to-end deep learning approach, DeepMI, to classify MI from Normal cases as well as identifying the time-occurrence of MI (defined as Acute, Recent and Old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level. In order to minimise computational overhead, we employ transfer learning using existing computer vision networks. Moreover, we use recurrent neural networks to encode the longitudinal information inherent in ECGs. We validated DeepMI on a dataset collected from 17, 381 patients, in which over 323, 000 samples were extracted per ECG lead. We were able to classify Normal cases as well as Acute, Recent and Old onset cases of MI, with AUROCs of 96. 7%, 82. 9%, 68. 6% and 73. 8%, respectively. We have demonstrated a multi-lead fusion approach to detect the presence and occurrence-time of MI. Our end-to-end framework provides flexibility for different levels of multi-lead ECG fusion and performs feature extraction via transfer learning.

TCS Journal 2021 Journal Article

Multi-matching nested relations

Jin Liu
Zhenhua Duan
Cong Tian

Multi-matching nested relation consists of a sequence of linearly ordered positions, call, internal, and return, augmented with one-to-one, one-to-n or n-to-one matching nested edges from call to return. For clarity, inner-call and inner-return are defined in n-to-one and one-to-n matching nested relations respectively. After word encoding by introducing tagged letters, Multi-matching Nested Words (MNWs) are obtained over a tagged alphabet. Then Multi-matching Nested Expression (MNE) and Multi-matching Nested Traceable Automaton (MNTA) are defined over MNWs. The closure properties of languages over MNWs are studied, including union, intersection, concatenation, Kleene-* and complementation. Moreover, nondeterministic MNTAs are as expressive as deterministic ones. Further, a transformation method from MNTAs to MNEs is proposed, where three kinds of labeled arcs are created for different transitions in order for the specific merging strategies. To specify the requirements of multi-matching nested calls and returns, we propose a temporal logic of Multi-matching Nested CAlls and RETurns (MNCARET). The abstract and matched-abstract versions of modalities are considered. For example, abstract-next operator allows a path to jump from a call to the first matched non-internal, which is the inner-call, inner-return or return, in a one-to-n or n-to-one matching relation while matched-abstract-next operator from a call directly to the matched return. We also present an approach to model check MNCARET formulas for the MNTA model, a subset of pushdown automata. This problem is reduced to the emptiness problem of Büchi MNTAs.

IJCAI Conference 2020 Conference Paper

Metamorphic Testing and Certified Mitigation of Fairness Violations in NLP Models

Pingchuan Ma
Shuai Wang
Jin Liu

Natural language processing (NLP) models have been increasingly used in sensitive application domains including credit scoring, insurance, and loan assessment. Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore, inspired by recent breakthroughs in the certified robustness of machine learning, we formulate NLP model fairness in a practical setting as (ε, k)-fairness and accordingly smooth the model predictions to mitigate fairness violations. We demonstrate our technique using popular (commercial) NLP models, and successfully flag thousands of discriminatory inputs that can cause fairness violations. We further enhance the evaluated models by adding certified fairness guarantee at a modest cost.

PDF Details DOI

YNIMG Journal 2020 Journal Article

The spatial organization of the chronnectome associates with cortical hierarchy and transcriptional profiles in the human brain

Jin Liu
Mingrui Xia
Xindi Wang
Xuhong Liao
Yong He

The chronnectome of the human brain represents dynamic connectivity patterns of brain networks among interacting regions, but its organization principle and related transcriptional signatures remain unclear. Using task-free fMRI data from the Human Connectome Project (681 participants) and microarray-based gene expression data from the Allen Institute for Brain Science (1791 brain tissue samples from six donors), we conduct a transcriptome-chronnectome association study to investigate the spatial configurations of dynamic brain networks and their linkages with transcriptional profiles. We first classify the dynamic brain networks into four categories of nodes according to their time-varying characteristics in global connectivity and modular switching: the primary sensorimotor regions with large global variations, the paralimbic/limbic regions with frequent modular switching, the frontoparietal cortex with both high global and modular dynamics, and the sensorimotor association cortex with limited dynamics. Such a spatial layout reflects the cortical functional hierarchy, microarchitecture, and primary connectivity gradient spanning from primary to transmodal areas, and the cognitive spectrum from perception to abstract processing. Importantly, the partial least squares regression analysis reveals that the transcriptional profiles could explain 28% of the variation in this spatial layout of network dynamics. The top-related genes in the transcriptional profiles are enriched for potassium ion channel complex and activity and mitochondrial part of the cellular component. These findings highlight the hierarchically spatial arrangement of dynamic brain networks and their coupling with the variation in transcriptional signatures, which provides indispensable implications for the organizational principle and cellular and molecular functions of spontaneous network dynamics.

YNIMG Journal 2019 Journal Article

Network analysis reveals disrupted functional brain circuitry in drug-naive social anxiety disorder

Xun Yang
Jin Liu
Yajing Meng
Mingrui Xia
Zaixu Cui
Xi Wu
Xinyu Hu
Wei Zhang

Social anxiety disorder (SAD) is a common and disabling condition characterized by excessive fear and avoidance of public scrutiny. Psychoradiology studies have suggested that the emotional and behavior deficits in SAD are associated with abnormalities in regional brain function and functional connectivity. However, little is known about whether intrinsic functional brain networks in patients with SAD are topologically disrupted. Here, we collected resting-state fMRI data from 33 drug-naive patients with SAD and 32 healthy controls (HC), constructed functional networks with 34 predefined regions based on previous meta-analytic research with task-based fMRI in SAD, and performed network-based statistic and graph-theory analyses. The network-based statistic analysis revealed a single connected abnormal circuitry including the frontolimbic circuit (termed the “fear circuit”, including the dorsolateral prefrontal cortex, ventral medial prefrontal cortex and insula) and posterior cingulate/occipital areas supporting perceptual processing. In this single altered network, patients with SAD had higher functional connectivity than HC. At the global level, graph-theory analysis revealed that the patients exhibited a lower normalized characteristic path length than HC, which suggests a disorder-related shift of network topology toward randomized configurations. SAD-related deficits in nodal degree, efficiency and participation coefficient were detected in the parahippocampal gyrus, posterior cingulate cortex, dorsolateral prefrontal cortex, insula and the calcarine sulcus. Aspects of abnormal connectivity were associated with anxiety symptoms. These findings highlight the aberrant topological organization of functional brain network organization in SAD, which provides insights into the neural mechanisms underlying excessive fear and avoidance of social interactions in patients with debilitating social anxiety.

TCS Journal 2015 Journal Article

Improved even order magic square construction algorithms and their applications in multi-user shared electronic accounts

Zhenhua Duan
Jin Liu
Jie Li
Cong Tian

This paper presents improved even order magic square construction algorithms, including both single even order magic square and double even order magic square construction algorithms. Further, in order to show how the algorithms work, two specific magic squares are constructed. Moreover, the correctness of the algorithms is proved, and the complexity analysis of the algorithms is given. Finally, the improved even order magic square construction algorithms are applied in secure communication and authentication areas for multi-user shared electronic account in detail.