Tao Li

EAAI Journal 2026 Journal Article

A fractional order-multimodal densely connected convolutional network approach for wind turbine yaw system abnormal noise diagnosis under small sample

• Tao Li
• Jiawei Yang
• Xiaoting Wu
• Yanan Chen
• Rongjun Ding
• Caichun He
• Jun Yang

Abnormal noise faults in the yaw system are one of the frequently encountered faults in the wind turbines, posing a serious threat to the safe and stable operation of the wind turbine. It is also the primary source of noise in the wind power system, significantly impacting the residents nearby. This paper proposes a fractional order-multimodal densely connected convolutional network (FO-MDESNET) approach for wind turbine yaw system abnormal noise diagnosis under small sample. The approach creates tri-modal input signals in time-domain, frequency-domain, and acoustic spectrogram to analyze yaw abnormal noise features. It overcomes the limitation of extracting features from single-modal input signals under small sample. The utilization of key features in small sample is further enhanced by the densely connected convolutional network (DenseNet), boosting its generalization ability. Mitigating gradient vanishing during computation and reducing overfitting risk through iterative computation of the DenseNet is optimized by momentum fractional order. This approach improves diagnosis accuracy of yaw abnormal noise faults under acoustic signals, surpassing traditional fault diagnosis approaches’ performance especially with fewer samples. This approach can lay an important foundation for the early acoustic-based fault diagnosis of key components and the entire system, as well as for the intelligent operation and maintenance of the wind power network.

EAAI Journal 2026 Journal Article

A pessimistic degree based large-scale group decision-making model under Interval-Valued Hesitant Fermatean Fuzzy sets

• Hongwu Qin
• Tao Li
• Xiuqin Ma
• Keqi Cheng
• Mengyao Wang

Large-scale group decision-making (LSGDM) presents complex challenges due to the inherent uncertainty of evaluation information and the intricate interactions among decision makers (DMs). While Interval-Valued Hesitant Fermatean Fuzzy Sets (IVHFFS) offer an effective tool for handling uncertainty, research on LSGDM within the Interval-Valued Hesitant Fermatean Fuzzy (IVHFF) environment remains unexplored. Furthermore, directly applying existing IVHFFS aggregation operators to large-scale scenarios causes severe data inflation, while traditional LSGDM frameworks in other contexts often rely on subjective consensus thresholds. To overcome these challenges, this study proposes an innovative threshold-free LSGDM model. We first introduce the concept of Pessimistic Degree (PD) to quantify DMs' behavioral characteristics. By extending the DEMATEL method to the IVHFF environment, we establish a comprehensive influence network that classifies DMs into distinct roles, enabling a novel interaction-based consensus reaching process (CRP) without predefined thresholds. Experimental results on a case study and comparative analyses confirm the model's superiority in reducing data inflation, avoiding information loss, and objectively facilitating consensus. This research provides a theoretically innovative framework for handling large-scale uncertainty and interactions.

AAAI Conference 2026 Conference Paper

A Solution Space Transformation-Guided Co-Evolution for Energy-Saving Distributed Heterogeneous Flexible Job Shop Scheduling

• Tao Li
• Xingchen Li
• Haoyue Ma
• Zhi-Hui Zhan

Solving energy-saving distributed heterogeneous flexible job shop scheduling problem (ES-DHFJSP) aims to enhance industrial production efficiency while minimizing energy consumption. State-of-the-art co-evolutionary algorithms have emerged as effective approaches for addressing ES-DHFJSP. However, existing methodologies demonstrate compromised convergence rates and excessive computational overhead when confronted with vast search spaces. In this work, we propose a novel solution space transformation-guided co-evolution algorithm (SSTCE) to overcome this limitation. In SSTCE, we first establish an inter-job similarity metric and incorporate constrained hierarchical clustering with optimal leaf ordering (CHC-OLO) to generate clustered job sets, which are subsequently utilized for population initialization that achieves a favorable balance between convergence and diversity. To enhance search capability in expansive solution spaces, we devise a dynamic solution space transformation mechanism that effectively reduces inefficient searches within the algorithm. Furthermore, we develop tailored local search strategies leveraging domain-specific knowledge of DHFJSP properties. Extensive experimental evaluations across 20 benchmark instances demonstrate that SSTCE significantly outperforms existing evolutionary algorithms in solving ES-DHFJSP.

EAAI Journal 2026 Journal Article

A text date-driven multi-criteria decision making method with linguistic intuitionistic multiplicative information and its application in product recommendation

• Liyuan Zhang
• Tao Li
• Huijuan Liu

Under the deep integration of artificial intelligence and big data technologies, decision making paradigms are shifting toward data-driven intelligent frameworks. As textual data constitutes a critical component of big data, its effective mining and interpretation are essential for enhancing decision quality. Unlike existing text mining-based decision making methods that rely on pre-defined alternatives or subjective criteria specification, we propose a new method to solve the problems about the generation of decision alternatives, extraction of decision criteria, and prioritization and optimization of decision alternatives under text data environment. Firstly, an improved Jaccard similarity measure combined with case-based reasoning is used to construct a set of initial alternatives. After that, correlated topic model and text mining techniques are then applied to derive decision criteria and their objective weights, while a linguistic intuitionistic multiplicative (LIM) priority model determines subjective weights. Then, a novel LIM interactive weighted averaging operator is introduced to rank the alternatives, and its key properties are also proved. Finally, a case study on computer recommendation demonstrates the method’s feasibility, interpretability, and practical effectiveness. Compared with some existing methods, the proposed method exhibits significant advantages in computational efficiency, topic modeling performance and scalability, proving its suitability for complex decision making in real-world big data environments.

AAAI Conference 2026 Conference Paper

Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild

• Jiatai Wang
• Zhiwei Xu
• Di Jin
• Xuewen Yang
• Tao Li

The proliferation of large language models (LLMs) has significantly advanced intelligent systems. Unfortunately, LLMs often face knowledge conflicts between internal memory and retrieved external information, arising from misinformation, biases, or outdated knowledge. These conflicts undermine response reliability and introduce uncertainty in decision-making. In this work, we analyze how LLMs navigate knowledge conflicts from an information-theoretic perspective and reveal that when conflicting and supplementary information exhibit significant differences, LLMs confidently resolve their preferences and alleviate the uncertainty during their response generation. When this difference is ambiguous, LLMs experience considerable uncertainty about their generation. Based on this insight, we propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models to adapt the retrieved information difference, facilitating robust response generation of LLMs even in conflicting contexts. Extensive experiments confirm our theoretical analysis and demonstrate the performance of Swin-VIB. Notably, Swin-VIB outperforms all competitive baselines in terms of the accuracy of the multiple-choice task, while improving the EM values in the open-ended QA task by at least 11.14%.

EAAI Journal 2026 Journal Article

Bridging local and global representations: An inter-and intra-window based transformer for unsupervised depth completion

• Tao Li
• Xiucheng Dong
• Jie Lin
• Yonghong Peng

Depth perception plays an important role in the tasks of autonomous driving and robot navigation. Unsupervised depth completion can generate dense depth maps from sparse depth measurements and aligned color images without the supervision of ground-truth annotations. As both local detail recovery and global semantic representation are crucial for unsupervised depth completion, unlike existing methods that rely solely on convolutional architectures, we propose a Transformer architecture, called inter-window and intra-window Transformer network, to leverage the long-range semantic modeling capability of Transformers. To bridge accurate local detail learning and efficient global representation within the Transformer architecture, we decompose the self-attention mechanism into parallel inter-window and intra-window self-attention. Specifically, the inter-window self-attention captures dependencies among window statistics to achieve efficient global context modeling. Moreover, for intra-window self-attention, point-to-plane distances are derived from depth features to guide the distinction of relevant and irrelevant image feature regions. Local attention is then applied to the arbitrary-shaped relevant regions to extract more informative and accurate image features. Extensive experiments on standard datasets, including Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI), New York University Depth Dataset Version 2 (NYUv2), and Visual Odometry with Inertial and Depth (VOID), demonstrate the superiority of our model over existing unsupervised methods. Compared to the state-of-the-art method Calibrated Backprojection Network (KBNet), our model achieves a 6. 4% improvement in Root Mean Squared Error (RMSE) on the outdoor KITTI dataset, a 6. 8% improvement on the indoor NYUv2 dataset, and a 2. 6% improvement on the indoor and outdoor VOID dataset.

AAAI Conference 2026 Conference Paper

EEG Agent: A Unified Framework for Automated EEG Analysis Using Large Language Models

• Sha Zhao
• Mingyi Peng
• Haiteng Jiang
• Tao Li
• Shijian Li

Scalable and generalizable analysis of brain activity is essential for advancing both clinical diagnostics and cognitive research. Electroencephalography (EEG), a non-invasive modality with high temporal resolution, has been widely used for brain states analysis. However, most exiting EEG models are usually tailored for single specific tasks, limiting their utility in realistic scenarios where EEG analysis often involves multi-task and continuous reasoning. In this work, we introduce EEG Agent, a general-purpose framework that leverages large language models (LLMs) to schedule and plan multiple tools to automatically complete EEG-related tasks. EEG Agent is capable of performing the key functions: EEG basic information perception, spatiotemporal EEG exploration, EEG event detection, interaction with users, and EEG report generation. To realize the capabilities, we design a toolbox composed of different tools for EEG preprocessing, feature extraction, event detection, etc. These capabilities were evaluated on public datasets, and our EEG Agent can support flexible and interpretable EEG analysis, highlighting its potential for real-world clinical applications.

AAAI Conference 2026 Conference Paper

EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation

• Shuhao Han
• Haotian Fan
• Jiachen Fu
• Liang Li
• Tao Li
• Junhui Cui
• Yunqiu Wang
• Yang Tai

Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated methods emerge to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated methods is constrained by the limited scale of existing datasets. Additionally, existing datasets lack the capacity to assess the performance of automated methods at a fine-grained level. In this study, we contribute an EvalMuse-40K dataset, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our dataset. This allows us to comprehensively evaluate the performance of image-text alignment methods for T2I models. Based on this dataset, we introduce an efficient automated evaluation method termed FGA-BLIP2, which enables Fine-Grained Alignment evaluation solely by inputting images and text leveraging BLIP2, without visual question answering for each fine-grained element. Experimental results show the proposed FGA-BLIP2 efficiently achieves good performance on multiple image-text alignment datasets. Meanwhile, benefiting from the high efficiency and fine-grained evaluation capability of FGA-BLIP2, we apply it as a reward model to improve text-to-image models, which effectively enhances the image-text alignment ability of text-to-image models.

JBHI Journal 2026 Journal Article

Evaluating Large Language Models in Crisis Detection: A Real-World Benchmark from Psychological Support Hotlines

• Guifeng Deng
• Shuying Rao
• Tianyu Lin
• Anlu Dai
• Pan Wang
• Junyi Xie
• Yue Pan
• Ke Zhao

Psychological support hotlines serve as critical lifelines for crisis intervention but encounter significant challenges due to rising demand and limited resources. Large language models (LLMs) offer potential support in crisis assessments, yet their effectiveness in emotionally sensitive, real-world clinical settings remains underexplored. We introduce PsyCrisisBench, a comprehensive benchmark of 540 annotated transcripts from the Hangzhou Psychological Assistance Hotline, assessing four key tasks: mood status recognition, suicidal ideation detection, suicide plan identification, and risk assessment. 64 LLMs across 15 model families—including closed-source (e. g. , GPT, Claude, Gemini) and open-source (e. g. , Llama, Qwen, DeepSeek)— were evaluated using zero-shot, few-shot, and fine-tuning paradigms. LLMs showed strong results in suicidal ideation detection (F1 = 0. 880), suicide plan identification (F1 = 0. 779), and risk assessment (F1 = 0. 907), with notable gains from few shot prompting and fine-tuning. Compared to trained human operators, LLMs achieved comparable or superior performance on suicide plan identification and risk assessment, while humans retained advantages on mood status recognition and suicidal ideation detection. Mood status recognition remained challenging (max F1 = 0. 709), likely due to missing vocal cues and semantic ambiguity. Notably, a fine-tuned 1. 5B-parameter model (Qwen2. 5-1. 5B) outperformed larger models on mood and suicidal ideation tasks. LLMs demonstrate performance broadly comparable to trained human operators in text-based crisis assessment, with complementary strengths across task types. PsyCrisisBench provides a robust, real-world evaluation framework to guide future model development and ethical deployment in clinical mental health.

EAAI Journal 2026 Journal Article

Neural network-driven predictive control and fractional-order nonlinear filter optimization for helicopter active vibration control

• Tao Li
• Minqi Wang
• Yaxin Zhang
• Lida Wang
• Rongjun Ding
• Jun Yang

The vibration problem in helicopters is a critical factor that affects both flight safety and passenger comfort. Active control is essential for vibration reduction, but several challenges are often encountered, such as phase delay in response, low system control accuracy, and slow convergence of control signals. This study explores the use of artificial intelligence (AI) to address the helicopter vibration reduction problem by proposing an approach based on neural network-driven predictive control and fractional-order nonlinear filter (N-PC-FNF) optimization for helicopter active vibration control. The approach first employs a bidirectional long short-term memory (BiLSTM) neural network to predict the time series of helicopter vibration signals, laying the foundation for the subsequent calculation of reverse vibration reduction signals in advance. Next, a fractional-order nonlinear filter combined with variational mode decomposition (VMD) is designed to decompose the complex vibration signals into intrinsic mode functions (IMFs) with distinct frequency domain characteristics. The fractional-order parameters are flexibly adjusted to better adapt to the nonlinear dynamic variations in the vibration signals. Finally, the weights of the filter are transferred to a multilayer perceptron (MLP) network for training, enabling the calculation of the filter’s steady-state weights and the actual actuator output signals, thereby achieving active control of helicopter vibrations. The research demonstrates that the proposed approach, which integrates neural network-driven predictive control with fractional-order nonlinear filter optimization, effectively realizes helicopter active vibration control and meets the requirements of engineering applications.

AAAI Conference 2026 Conference Paper

Nighttime Flare Removal via Wavelet-Guided and Gated-Enhanced Spatial-Frequency Fusion Network

• Yun Liu
• Guang Yang
• Tao Li
• Weisi Lin

Nighttime flares, caused by complex scattering and reflections from artificial light sources, significantly degrade image quality and hinder downstream visual tasks. Existing deflare networks usually struggle to jointly capture and fuse latent spatial and frequency features. In this paper, we propose a novel Wavelet-guided and Gated-enhanced Spatial-frequency Fusion Network (WGSF-Net) for nighttime flare removal. WGSF-Net is primarily composed of two key modules: Wavelet-guided Fusion Block (WFB) and Local-Global Block (LGB). Specifically, WFB integrates a Multi-level Wavelet Enhancement Block (MWEB) and a Spatial-Frequency Fusion Network (SFFN) to effectively extract hierarchical spatial and frequency features through a coarse-to-fine strategy based on multi-level wavelet decomposition. To better suppress flare artifacts, LGB is designed to jointly capture local and global information: a Gated-Enhanced Attention Block (GEAB) selectively amplifies critical local features through a gated network and a difference network, and the subsequent SFFN performs global spatial-frequency fusion via depthwise separable convolution and partial Fourier convolution. This design enables LGB to effectively disentangle flare-corrupted regions and restore fine-grained details, making it particularly suited for challenging real-world flare scenarios. Extensive experiments on both synthetic and real datasets show that WGSF-Net achieves state-of-the-art performance in nighttime flare removal, outperforming existing methods across five evaluation metrics.

JBHI Journal 2026 Journal Article

SSDiff: A Contrast-Free Virtual LGE Generator for Acute Myocardial Infarction with Joint Segmentation via Diffusion Model

• Jing Qi
• Xiuzheng Yue
• Miao Hu
• Xin Wen
• Yinyin Chen
• Hang Jin
• Chengyan Wang
• Tao Li

Myocardial infarction (MI) remains a major cause of death and disability. Although late gadolinium enhancement (LGE) cardiac MRI is the reference for assessing myocardial viability, it requires contrast injection, complex protocols, and added cost. Prior virtual LGE approaches-mostly GAN-based-mainly use cine or T1 mapping and ignore T2-weighted short-tau inversion recovery (T2-STIR), which is highly sensitive to edema in acute MI. They also typically require manual post-hoc delineation of infarcts. We propose SSDiff ( S ynthesis joint S egmentation Diff usion), a multitask conditional diffusion framework that synthesizes contrast-free virtual LGE from routine cine + T2-STIR for acute infarct assessment and simultaneously segments myocardium, ventricular blood pool, and infarct. SSDiff introduces a feature-disentangled attention module that isolates sequence-specific cues to steer the diffusion process, and a cross-fusion module that aligns synthesis and segmentation decoders for mutual optimization. Evaluated on a multi-center, multi-vendor dataset of 409 subjects (2, 177 aligned cine-T2-STIR-LGE triplets), SSDiff yields significant gains in synthetic image quality and downstream segmentation accuracy over strong baselines. Beyond serving as a clinically feasible alternative when LGE is unavailable or contraindicated, SSDiff also generates paired image-mask samples that augment LGE-scarce training, highlighting its practical utility and translational potential. Code is available at: https://github.com/QijingGJ/SSDiff.

EAAI Journal 2025 Journal Article

A novel group decision-making method for incomplete interval-valued intuitionistic multiplicative linguistic preference relations

• Tao Li
• Liyuan Zhang

By conducting pairwise comparisons, decision-makers can construct interval-valued intuitionistic multiplicative linguistic preference relations (IVIMLPRs) to express the asymmetrically uncertain preferred and non-preferred qualitative judgments. Based on the consistency and consensus analysis, this paper proposes a new group decision-making (GDM) method with incomplete IVIMLPRs. Firstly, a reasonable and rational concept for IVIMLPR is defined. Inspired by the consistent intuitionistic multiplicative linguistic preference relations (IMLPRs), the consistency of IVIMLPRs is expressed by considering the corresponding lower and upper IMLPRs. After that, the acceptably consistent IVIMLPR is further introduced. Based on these concepts, two optimization models are constructed to estimate the missing linguistic variables and adjust an unacceptably consistent IVIMLPR, respectively. To obtain the priority weights from IVIMLPR in a reliable way, the consistency modeling method is employed. Before calculating the collective IVIMLPR, the weights of decision-makers are determined. Subsequently, the consensus analysis is conducted. If the consensus of an IVIMLPR is insufficient, a mathematical model is established to enhance the consensus level. Finally, the applications of the proposed GDM approach are offered and the comparative analysis is discussed. Compared with some existing methods, the proposed decision-making algorithm can perform a rational and effective process in the field of artificial intelligence computing.

EAAI Journal 2025 Journal Article

An integrated exergy efficiency and machine learning method for optimizing organic solid waste gasification process

• Wenni Chen
• Xianan Xiang
• Sha Liu
• Jun Guo
• Tao Li
• Xuehua Zhou
• Deyong Peng
• Zhiya Deng

Organic solid waste (OSW) gasification is a critical pathway toward sustainable energy utilization. This study develops an integrated prediction model by combining exergy efficiency-based analytic hierarchy process-fuzzy comprehensive evaluation (AHP-FCE) with machine learning techniques. The model aims to select the optimal gasifier type and operational parameters based on OSW characteristics and processing capacities. Exergy efficiency derived from experimental data is used to construct AHP-FCE scores, which are then predicted using eight machine learning algorithms. Gradient boosting decision tree (GBDT) achieves the best performance. The prediction model is applied to three practical cases. For a project with an annual processing capacity of 2000 tons of refuse-derived fuel (RDF), the model consistently recommends the downdraft fixed-bed gasifier (DBG). In a corn straw gasification project processing 11, 000 tons per year, the bubbling fluidized-bed gasifier (BBG) is identified as the optimal choice. For a bamboo chip gasification project with an annual capacity of 150, 000 tons, the model suggests using the circulating fluidized-bed gasifier (CFBG) for reduction objectives and the dual fluidized-bed gasifier (DFBG) for hydrogen production goals. Additionally, the model shows significant potential. It can also be applied to optimize other complex systems that require balancing multiple influencing factors.

ICLR Conference 2025 Conference Paper

BrainUICL: An Unsupervised Individual Continual Learning Framework for EEG Applications

• Yangxuan Zhou
• Sha Zhao
• Jiquan Wang
• Haiteng Jiang
• Shijian Li
• Tao Li
• Gang Pan 0001

Electroencephalography (EEG) is a non-invasive brain-computer interface technology used for recording brain electrical activity. It plays an important role in human life and has been widely uesd in real life, including sleep staging, emotion recognition, and motor imagery. However, existing EEG-related models cannot be well applied in practice, especially in clinical settings, where new patients with individual discrepancies appear every day. Such EEG-based model trained on fixed datasets cannot generalize well to the continual flow of numerous unseen subjects in real-world scenarios. This limitation can be addressed through continual learning (CL), wherein the CL model can continuously learn and advance over time. Inspired by CL, we introduce a novel Unsupervised Individual Continual Learning paradigm for handling this issue in practice. We propose the BrainUICL framework, which enables the EEG-based model to continuously adapt to the incoming new subjects. Simultaneously, BrainUICL helps the model absorb new knowledge during each adaptation, thereby advancing its generalization ability for all unseen subjects. The effectiveness of the proposed BrainUICL has been evaluated on three different mainstream EEG tasks. The BrainUICL can effectively balance both the plasticity and stability during CL, achieving better plasticity on new individuals and better stability across all the unseen individuals, which holds significance in a practical setting.

ICLR Conference 2025 Conference Paper

CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

• Jiquan Wang
• Sha Zhao
• Zhiling Luo
• Yangxuan Zhou
• Haiteng Jiang
• Shijian Li
• Tao Li
• Gang Pan 0001

Electroencephalography (EEG) is a non-invasive technique to measure and record brain electrical activity, widely used in various BCI and healthcare applications. Early EEG decoding methods rely on supervised learning, limited by specific tasks and datasets, hindering model performance and generalizability. With the success of large language models, there is a growing body of studies focusing on EEG foundation models. However, these studies still leave challenges: Firstly, most of existing EEG foundation models employ full EEG modeling strategy. It models the spatial and temporal dependencies between all EEG patches together, but ignores that the spatial and temporal dependencies are heterogeneous due to the unique structural characteristics of EEG signals. Secondly, existing EEG foundation models have limited generalizability on a wide range of downstream BCI tasks due to varying formats of EEG data, making it challenging to adapt to. To address these challenges, we propose a novel foundation model called CBraMod. Specifically, we devise a criss-cross transformer as the backbone to thoroughly leverage the structural characteristics of EEG signals, which can model spatial and temporal dependencies separately through two parallel attention mechanisms. And we utilize an asymmetric conditional positional encoding scheme which can encode positional information of EEG patches and be easily adapted to the EEG with diverse formats. CBraMod is pre-trained on a very large corpus of EEG through patch-based masked EEG reconstruction. We evaluate CBraMod on up to 10 downstream BCI tasks (12 public datasets). CBraMod achieves the state-of-the-art performance across the wide range of tasks, proving its strong capability and generalizability. The source code is publicly available at https://github.com/wjq-learning/CBraMod.

AAAI Conference 2025 Conference Paper

Enhancing Generalizability via Utilization of Unlabeled Data for Occupancy Perception

• Ruihang Li
• Tao Li
• Shanding Ye
• Kaikai Xiao
• Zheng Huangnan
• Zhe Yin
• Zhijie Pan

3D occupancy perception accurately estimates the volumetric status and semantic labels of a scene, attracting significant attention in the field of autonomous driving. However, enhancing the model's ability to generalize across different driving scenarios or sensing systems, often requires redesigning the model or extra-expensive annotations. To this end, following a comprehensive analysis of the occupancy model architecture, we proposed the UGOCC method that utilizes domain adaptation to efficiently harness unlabeled autonomous driving data, thereby enhancing the model's generalizability. Specifically, we design the depth fusion module by employing self-supervised depth estimation, and propose a strategy based on semantic attention and domain adversarial learning to improve the generalizability of the learnable fusion module. Additionally, we propose an OCC-specific pseudo-label selection tailored for semi-supervised learning, which optimizes the overall network's generalizability. Our experiment results on two challenging datasets nuScenes and Waymo, demonstrate that our method not only achieves state-of-the-art generalizability but also enhances the model's perceptual capabilities within the source domain by utilizing unlabeled data.

ICML Conference 2025 Conference Paper

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

• Tao Li
• Zhengbao He
• Yujun Li
• Yasheng Wang
• Lifeng Shang
• Xiaolin Huang

Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing only low-rank matrices. Despite recent progress in improving LoRA’s performance, the relationship between the LoRA optimization space and the full parameter space is often overlooked. A solution that appears flat in the loss landscape of the LoRA space may still exhibit sharp directions in the full parameter space, potentially compromising generalization. We introduce Flat-LoRA, which aims to identify a low-rank adaptation situated in a flat region of the full parameter space. Instead of adopting the well-established sharpness-aware minimization approach, which incurs significant computation and memory overheads, we employ a Bayesian expectation loss objective to preserve training efficiency. Further, we design a refined strategy for generating random perturbations to enhance performance and carefully manage memory overhead using random seeds. Experiments across diverse tasks—including mathematical reasoning, coding abilities, dialogue generation, instruction following, and text-to-image generation—demonstrate that Flat-LoRA improves both in-domain and out-of-domain generalization. Code is available at https: //github. com/nblt/Flat-LoRA.

AAAI Conference 2025 Conference Paper

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

• Ao Liu
• Wenshan Li
• Tao Li
• Beibei Li
• Guangquan Xu
• Pan Zhou
• Wengang Ma
• Hanyuan Huang

End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing critical edges and thus manipulating the classification results. Current defenses, due to their persistent utilization of global-optimization-based end-to-end training schemes, inherently encapsulate the vulnerabilities of GNNs. This is specifically evidenced in their inability to defend against targeted secondary attacks. In this paper, we propose the Graph Agent Network (GAgN) to address the aforementioned vulnerabilities of GNNs. GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent. Through the decentralized interactions between agents, they can learn to infer global perceptions to perform tasks including inferring embeddings, degrees and neighbor relationships for given nodes. This empowers nodes to filtering adversarial edges while carrying out classification tasks. Furthermore, agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks. We prove that single-hidden-layer multilayer perceptrons (MLPs) are theoretically sufficient to achieve these functionalities. Experimental results show that GAgN effectively implements all its intended capabilities and, compared to state-of-the-art defenses, achieves optimal classification accuracy on the perturbed datasets.

AAAI Conference 2025 Conference Paper

Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending Against Poisoning Attacks

• Ao Liu
• Wenshan Li
• Beibei Li
• Wengang Ma
• Tao Li
• Pan Zhou

Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require substituting the original GNNs with defense models, regardless of the original's type. This approach, while targeting adversarial robustness, compromises the enhancements developed in prior research to boost GNNs' practical performance. Here we introduce Grimm, the first plug-and-play defense model. With just a minimal interface requirement for extracting features from any layer of the protected GNNs, Grimm is thus enabled to seamlessly rectify perturbations. Specifically, we utilize the feature trajectories (FTs) generated by GNNs, as they evolve through epochs, to reflect the training status of the networks. We then theoretically prove that the FTs of victim nodes will inevitably exhibit discriminable anomalies. Consequently, inspired by the natural parallelism between the biological nervous and immune systems, we construct Grimm, a comprehensive artificial immune system for GNNs. Grimm not only detects abnormal FTs and rectifies adversarial edges during training but also operates efficiently in parallel, thereby mirroring the concurrent functionalities of its biological counterparts. We experimentally confirm that Grimm offers four empirically validated advantages: 1) Harmlessness, as it does not actively interfere with GNN training; 2) Parallelism, ensuring monitoring, detection, and rectification functions operate independently of the GNN training process; 3) Generalizability, demonstrating compatibility with mainstream GNNs such as GCN, GAT, and GraphSAGE; and 4) Transferability, as the detectors for abnormal FTs can be efficiently transferred across different systems for one-step rectification.

AAAI Conference 2025 Conference Paper

Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation

• Yangxuan Zhou
• Sha Zhao
• Jiquan Wang
• Haiteng Jiang
• Shijian Li
• Benyan Luo
• Tao Li
• Gang Pan

Sleep staging is important for monitoring sleep quality and diagnosing sleep-related disorders. Recently, numerous deep learning-based models have been proposed for automatic sleep staging using polysomnography recordings. Most of them are trained and tested on the same labeled datasets which results in poor generalization to unseen target domains. However, they regard the subjects in the target domains as a whole and overlook the individual discrepancies, which limits the model's generalization ability to new patients (i.e., unseen subjects) and plug-and-play applicability in clinics. To address this, we propose a novel Source-Free Unsupervised Individual Domain Adaptation (SF-UIDA) framework for sleep staging, leveraging sequential cross-view contrasting and pseudo-label based fine-tuning. It is actually a two-step subject-specific adaptation scheme, which enables the source model to effectively adapt to newly appeared unlabeled individual without access to the source data. It meets the practical needs in real-world scenarios, where the personalized customization can be plug-and-play applied to new ones. Our framework is applied to three classic sleep staging models and evaluated on three public sleep datasets, achieving the state-of-the-art performance.

NeurIPS Conference 2025 Conference Paper

SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding

• Yangxuan Zhou
• Sha Zhao
• Jiquan Wang
• Haiteng Jiang
• Shijian Li
• Tao Li
• Gang Pan

Human brain achieves dynamic stability-plasticity balance through synaptic homeostasis, a self-regulatory mechanism that stabilizes critical memory traces while preserving optimal learning capacities. Inspired by this biological principle, we propose SPICED: a neuromorphic framework that integrates the synaptic homeostasis mechanism for unsupervised continual EEG decoding, particularly addressing practical scenarios where new individuals with inter-individual variability emerge continually. SPICED comprises a novel synaptic network that enables dynamic expansion during continual adaptation through three bio-inspired neural mechanisms: (1) critical memory reactivation, which mimics brain functional specificity, selectively activates task-relevant memories to facilitate adaptation; (2) synaptic consolidation, which strengthens these reactivated critical memory traces and enhances their replay prioritizations for further adaptations and (3) synaptic renormalization, which are periodically triggered to weaken global memory traces to preserve learning capacities. The interplay within synaptic homeostasis dynamically strengthens task-discriminative memory traces and weakens detrimental memories. By integrating these mechanisms with continual learning system, SPICED preferentially replays task-discriminative memory traces that exhibit strong associations with newly emerging individuals, thereby achieving robust adaptations. Meanwhile, SPICED effectively mitigates catastrophic forgetting by suppressing the replay prioritization of detrimental memories during long-term continual learning. Validated on three EEG datasets, SPICED show its effectiveness. More importantly, SPICED bridges biological neural mechanisms and artificial intelligence through synaptic homeostasis, providing insights into the broader applicability of bio-inspired principles.

ECAI Conference 2025 Conference Paper

Towards Mitigation of Hallucination for LLM-Empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor

• Siyuan Liu
• Wenjing Liu
• Zhiwei Xu
• Xin Wang
• Bo Chen
• Tao Li

Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs—where outputs are inconsistent with facts—pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed by hallucinations of intelligent agents, we present HalMit, a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents and thus detect hallucinations without requiring internal knowledge of the LLM’s architecture. Specifically, a probabilistic fractal sampling technique is proposed to generate a sufficient number of queries to trigger the incredible responses in parallel, efficiently identifying the generalization bound of the target agent. Experimental evaluations demonstrate that HalMit significantly outperforms existing approaches in hallucination monitoring. Its black-box nature and superior performance make HalMit a promising solution for enhancing the dependability of LLM-powered systems.

IROS Conference 2025 Conference Paper

Towards Robust Sensor-Fusion Ground SLAM: A Comprehensive Benchmark and A Resilient Framework

• Deteng Zhang
• Junjie Zhang
• Yan Sun
• Tao Li
• Hao Yin
• Hongzhao Xie
• Jie Yin

Considerable advancements have been achieved in SLAM methods tailored for structured environments, yet their robustness under challenging corner cases remains a critical limitation. Although multi-sensor fusion approaches integrating diverse sensors have shown promising performance improvements, the research community faces two key barriers: On one hand, the lack of standardized and configurable benchmarks that systematically evaluate SLAM algorithms under diverse degradation scenarios hinders comprehensive performance assessment. While on the other hand, existing SLAM frameworks primarily focus on fusing a limited set of sensor types, without effectively addressing adaptive sensor selection strategies for varying environmental conditions. To bridge these gaps, we make three key contributions: First, we introduce M3DGR dataset: a sensor-rich benchmark with systematically induced degradation patterns including visual challenge, LiDAR degeneracy, wheel slippage and GNSS denial. Second, we conduct a comprehensive evaluation of forty SLAM systems on M3DGR, providing critical insights into their robustness and limitations under challenging real-world conditions. Third, we develop a resilient modular multi-sensor fusion framework named Ground-Fusion++, which demonstrates robust performance by coupling GNSS, RGB-D, LiDAR, IMU (Inertial Measurement Unit) and wheel odometry. Codes 1 and datasets 2 are publicly available.

JBHI Journal 2025 Journal Article

UA-VLFM: An Uncertainty-aware Vision-Language Foundation Model for Auxiliary Diagnosis of Vitreoretinal Iymphoma

• Wenwen Wang
• Aidi Lin
• Tian Lin
• Zhen Liang
• Kai Xu
• Tao Li
• Dan Liang
• Shanshan Yu

Vitreoretinal lymphoma (VRL) is a rare malignant ocular tumor, and its early diagnosis is crucial for patient prognosis. However, due to its insidious and diverse clinical manifestations, it is often misdiagnosed as other ophthalmic diseases, leading to blindness or even fatal outcomes. In this study, an uncertainty-aware visionlanguage foundational model (UA-VLFM) based on contrastive learning and uncertainty estimation is developed to achieve automatic classification of VRL and other 5 retinal diseases. First, we integrate MAE-based pretraining knowledge on large-scale optical coherence tomography (OCT) images and efficient Low-rank adaption (LoRA) optimization strategy to enhance the representation ability and optimization efficiency of the model. Moreover, an uncertainty-aware contrastive learning method based on Dirichlet distribution within the contrastive vision-language pretraining framework is proposed to further align vision and language feature in the high-dimensional embedding space and obtain prediction results with corresponding uncertainty scores, thereby enhancing the reliability of VRL diagnosis. In the test dataset with 5, 563 OCT images, UA-VLFM achieves a higher average F1 score of 0. 9684 than other state-of-the-art algorithms (0. 8186-0. 9427) and improves to 0. 9839 with the threshold strategy. Notably, the proposed UA-VLFM achieves an F1 score of 0. 9217 and 0. 9544 before and after thresholding on VRL, the most challenging category, significantly outperforming other methods (0. 5089-0. 9366 and 0. 6639-0. 9133). Our UA-VLFM provides a trustworthy method for aiding in the diagnosis of VRL on retinal OCT images. The code has been released on Github: https://github.com/wang-wen-wen/UA-VLFM.

EAAI Journal 2024 Journal Article

A behavior three-way decision approach under interval-valued triangular fuzzy numbers with application to the selection of additive manufacturing composites

• Guoquan Xie
• Wanying Zhu
• Jiangyang Xiang
• Tao Li
• Xuan Wu
• Yong Peng
• Honghao Zhang
• Kui Wang

Additive manufacturing composites, also recognized as three-dimensional (3D) printing composites, are highly anticipated for their potential to replace industrial materials due to the availability of multiple printing processes and optional materials. However, research gaps exist in cognitive deficiencies and psychological behaviors of decision-makers, as well as experimental error effects caused by material testing, resulting in material selection as a challenging issue. Therefore, this study proposes a novel behavior three-way decision model under the interval-valued triangular fuzzy number (IVTFN) to settle the selection issue of 3D printing composites. The research contributions are summarized as follows. First, the IVTFN is presented to account for the impacts of cognitive deficiency and experimental errors, based on which the concepts of information entropy and fuzzy measure are further developed to conduct the criterion weights. In addition, by integrating the prospect theory and regret theory, a framework for constructing the behavioral decision matrix is presented. Moreover, a novel behavior three-way decision model with the perspectives of objective and preference is proposed to classify the decision region. This study presents a comprehensive methodology integrating the three-way decision model and multi-criteria decision-making method to achieve both alternative ranking and alternative classifying. Finally, a research case of 3D printing composites reinforced by continuous hybrid fibers is adopted to illustrate the validity of the methodology. Comparative analysis and sensitivity analysis are also performed. This study offers valuable insights and tools for systematically tackling the 3D printing composite material selection issues.

JBHI Journal 2024 Journal Article

CareSleepNet: A Hybrid Deep Learning Network for Automatic Sleep Staging

• Jiquan Wang
• Sha Zhao
• Haiteng Jiang
• Yangxuan Zhou
• Zhenghe Yu
• Tao Li
• Shijian Li
• Gang Pan

Sleep staging is essential for sleep assessment and plays an important role in disease diagnosis, which refers to the classification of sleep epochs into different sleep stages. Polysomnography (PSG), consisting of many different physiological signals, e. g. electroencephalogram (EEG) and electrooculogram (EOG), is a gold standard for sleep staging. Although existing studies have achieved high performance on automatic sleep staging from PSG, there are still some limitations: 1) they focus on local features but ignore global features within each sleep epoch, and 2) they ignore cross-modality context relationship between EEG and EOG. In this paper, we propose CareSleepNet, a novel hybrid deep learning network for automatic sleep staging from PSG recordings. Specifically, we first design a multi-scale Convolutional-Transformer Epoch Encoder to encode both local salient wave features and global features within each sleep epoch. Then, we devise a Cross-Modality Context Encoder based on co-attention mechanism to model cross-modality context relationship between different modalities. Next, we use a Transformer-based Sequence Encoder to capture the sequential relationship among sleep epochs. Finally, the learned feature representations are fed into an epoch-level classifier to determine the sleep stages. We collected a private sleep dataset, SSND, and use two public datasets, Sleep-EDF-153 and ISRUC to evaluate the performance of CareSleepNet. The experiment results show that our CareSleepNet achieves the state-of-the-art performance on the three datasets. Moreover, we conduct ablation studies and attention visualizations to prove the effectiveness of each module and to analyze the influence of each modality.

NeurIPS Conference 2024 Conference Paper

Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection

• Yu Zhang
• Ruoyu Li
• Nengwu Wu
• Qing Li
• Xinhan Lin
• Yang Hu
• Tao Li
• Yong Jiang

In high-stakes sectors such as network security, IoT security, accurately distinguishing between normal and anomalous data is critical due to the significant implications for operational success and safety in decision-making. The complexity is exacerbated by the presence of unlabeled data and the opaque nature of black-box anomaly detection models, which obscure the rationale behind their predictions. In this paper, we present a novel method to interpret the decision-making processes of these models, which are essential for detecting malicious activities without labeled attack data. We put forward the Segmentation Clustering Decision Tree (SCD-Tree), designed to dissect and understand the structure of normal data distributions. The SCD-Tree integrates predictions from the anomaly detection model into its splitting criteria, enhancing the clustering process with the model's insights into anomalies. To further refine these segments, the Gaussian Boundary Delineation (GBD) algorithm is employed to define boundaries within each segmented distribution, effectively delineating normal from anomalous data points. At this point, this approach addresses the curse of dimensionality by segmenting high-dimensional data and ensures resilience to data drift and perturbations through flexible boundary fitting. We transform the intricate operations of anomaly detection into an interpretable rule's format, constructing a comprehensive set of rules for understanding. Our method's evaluation on diverse datasets and models demonstrates superior explanation accuracy, fidelity, and robustness over existing method, proving its efficacy in environments where interpretability is paramount.

AAAI Conference 2024 Conference Paper

Generalizable Sleep Staging via Multi-Level Domain Alignment

• Jiquan Wang
• Sha Zhao
• Haiteng Jiang
• Shijian Li
• Tao Li
• Gang Pan

Automatic sleep staging is essential for sleep assessment and disorder diagnosis. Most existing methods depend on one specific dataset and are limited to be generalized to other unseen datasets, for which the training data and testing data are from the same dataset. In this paper, we introduce domain generalization into automatic sleep staging and propose the task of generalizable sleep staging which aims to improve the model generalization ability to unseen datasets. Inspired by existing domain generalization methods, we adopt the feature alignment idea and propose a framework called SleepDG to solve it. Considering both of local salient features and sequential features are important for sleep staging, we propose a Multi-level Feature Alignment combining epoch-level and sequence-level feature alignment to learn domain-invariant feature representations. Specifically, we design an Epoch-level Feature Alignment to align the feature distribution of each single sleep epoch among different domains, and a Sequence-level Feature Alignment to minimize the discrepancy of sequential features among different domains. SleepDG is validated on five public datasets, achieving the state-of-the-art performance.

AAAI Conference 2024 Conference Paper

MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis

• Wenhao Guan
• Yishuang Li
• Tao Li
• Hukai Huang
• Feng Wang
• Jiayan Lin
• Lingyan Huang
• Lin Li

The style transfer task in Text-to-Speech (TTS) refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches are either based on fixed emotional labels or reference speech clips, which cannot achieve flexible style transfer. Recently, some methods have adopted text descriptions to guide style transfer. In this paper, we propose a more flexible multi-modal and style controllable TTS framework named MM-TTS. It can utilize any modality as the prompt in unified multi-modal prompt space, including reference speech, emotional facial images, and text descriptions, to control the style of the generated speech in a system. The challenges of modeling such a multi-modal style controllable TTS mainly lie in two aspects: 1) aligning the multi-modal information into a unified style space to enable the input of arbitrary modality as the style prompt in a single system, and 2) efficiently transferring the unified style representation into the given text content, thereby empowering the ability to generate prompt style-related voice. To address these problems, we propose an aligned multi-modal prompt encoder that embeds different modalities into a unified style space, supporting style transfer for different modalities. Additionally, we present a new adaptive style transfer method named Style Adaptive Convolutions (SAConv) to achieve a better style representation. Furthermore, we design a Rectified Flow based Refiner to solve the problem of over-smoothing Mel-spectrogram and generate audio of higher fidelity. Since there is no public dataset for multi-modal TTS, we construct a dataset named MEAD-TTS, which is related to the field of expressive talking head. Our experiments on the MEAD-TTS dataset and out-of-domain datasets demonstrate that MM-TTS can achieve satisfactory results based on multi-modal prompts. The audio samples and constructed dataset are available at https://multimodal-tts.github.io.

EAAI Journal 2024 Journal Article

Multi-objective modeling of price and pollution in large-scale energy hubs with load management

• Shuangbin Ma
• Tao Li
• Jun Ni
• Jinxin Chen
• Ji Li

This study introduces a novel multi-objective model that addresses emission costs, large-scale user operational expenses, and the efficiency of the electric storage system within an integrated energy hub encompassing heating, water, power, and gas sources. A key objective of this model is to maximize the performance of the electrical storage system. The study employs the epsilon-constraint method to construct the Pareto front, aiming to balance profitability and emission reduction from virtual power plant units. The final decision-making process utilizes a fuzzy decision-making technique. Additionally, demand response program (DRP) is incorporated to optimize peak-hour demand and align the load profile with defined objectives. The proposed approach is evaluated across various operational scenarios within a sample system, demonstrating its effectiveness and potential benefits in terms of cost reduction and environmental impact mitigation. Focusing on environmental impact, the carbon dioxide (CO2) emissions are also lower under the DRP scenario, amounting to 10253. 92 kg without DRP versus 10127. 74 kg with DRP. This reduction in emissions aligns with sustainable energy management goals, showcasing DRP's capability to mitigate environmental impacts associated with energy generation and consumption. The percentage improvements in total costs and emissions further highlight the advantages of employing DRP. The reductions in total costs range from approximately 1. 2%–1. 4%, demonstrating cost savings across different cost categories. Similarly, the decrease in CO2 emissions by approximately 1. 2% underscores DRP's role in promoting environmentally friendly energy practices.

JBHI Journal 2024 Journal Article

NKUT: Dataset and Benchmark for Pediatric Mandibular Wisdom Teeth Segmentation

• Zhenhuan Zhou
• Yuzhu Chen
• Along He
• Xitao Que
• Kai Wang
• Rui Yao
• Tao Li

Germectomy is a common surgery in pediatric dentistry to prevent the potential dangers caused by impacted mandibular wisdom teeth. Segmentation of mandibular wisdom teeth is a crucial step in surgery planning. However, manually segmenting teeth and bones from 3D volumes is time-consuming and may cause delays in treatment. Deep learning based medical image segmentation methods have demonstrated the potential to reduce the burden of manual annotations, but they still require a lot of well-annotated data for training. In this paper, we initially curated a Cone Beam Computed Tomography (CBCT) dataset, NKUT, for the segmentation of pediatric mandibular wisdom teeth. This marks the first publicly available dataset in this domain. Second, we propose a semantic separation scale-specific feature fusion network named WTNet, which introduces two branches to address the teeth and bones segmentation tasks. In WTNet, We design a Input Enhancement (IE) block and a Teeth-Bones Feature Separation (TBFS) block to solve the feature confusions and semantic-blur problems in our task. Experimental results suggest that WTNet performs better on NKUT compared to previous state-of-the-art segmentation methods (such as TransUnet), with a maximum DSC lead of nearly 16%.

TMLR Journal 2024 Journal Article

Online Continual Learning via Logit Adjusted Softmax

• Zhehao Huang
• Tao Li
• Chenhe Yuan
• Yingwen Wu
• Xiaolin Huang

Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting, leading to model prediction bias towards recently learned classes. In this paper, we theoretically analyze that inter-class imbalance is entirely attributed to imbalanced class-priors, and the function learned from intra-class intrinsic distributions is the optimal classifier that minimizes the class-balanced error. To that end, we present that a simple adjustment of model logits during training can effectively resist prior class bias and pursue the corresponding optimum. Our proposed method, Logit Adjusted Softmax, can mitigate the impact of inter-class imbalance not only in class-incremental but also in realistic scenarios that sum up class and domain incremental learning, with little additional computational cost. We evaluate our approach on various benchmarks and demonstrate significant performance improvements compared to prior arts. For example, our approach improves the best baseline by 4.6% on CIFAR10.

NeurIPS Conference 2024 Conference Paper

Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise

• Zhenning Shi
• Haoshuai Zheng
• Chen Xu
• Changsheng Dong
• Bin Pan
• Xueshuo Xie
• Along He
• Tao Li

Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https: //github. com/nkicsl/Resfusion.

TMLR Journal 2024 Journal Article

Revisiting Random Weight Perturbation for Efficiently Improving Generalization

• Tao Li
• Qinghua Tao
• Weihao Yan
• Yingwen Wu
• Zehao Lei
• Kun Fang
• Mingzhen He
• Xiaolin Huang

Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning. Two branches of methods have been proposed to seek flat minima and improve generalization: one led by sharpness-aware minimization (SAM) minimizes the worst-case neighborhood loss through adversarial weight perturbation (AWP), and the other minimizes the expected Bayes objective with random weight perturbation (RWP). While RWP offers advantages in computation and is closely linked to AWP on a mathematical basis, its empirical performance has consistently lagged behind that of AWP. In this paper, we revisit the use of RWP for improving generalization and propose improvements from two perspectives: i) the trade-off between generalization and convergence and ii) the random perturbation generation. Through extensive experimental evaluations, we demonstrate that our enhanced RWP methods achieve greater efficiency in enhancing generalization, particularly in large-scale problems, while also offering comparable or even superior performance to SAM. The code is released at https://github.com/nblt/mARWP.

AAAI Conference 2024 Conference Paper

Towards Inductive Robustness: Distilling and Fostering Wave-Induced Resonance in Transductive GCNs against Graph Adversarial Attacks

• Ao Liu
• Wenshan Li
• Tao Li
• Beibei Li
• Hanyuan Huang
• Pan Zhou

Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such attacks inherit the transductive limitations of graph convolutional networks (GCNs). As a result, they are constrained by fixed structures and do not naturally generalize to unseen nodes. Here, we discover that transductive GCNs inherently possess a distillable robustness, achieved through a wave-induced resonance process. Based on this, we foster this resonance to facilitate inductive and robust learning. Specifically, we first prove that the signal formed by GCN-driven message passing (MP) is equivalent to the edge-based Laplacian wave, where, within a wave system, resonance can naturally emerge between the signal and its transmitting medium. This resonance provides inherent resistance to malicious perturbations inflicted on the signal system. We then prove that merely three MP iterations within GCNs can induce signal resonance between nodes and edges, manifesting as a coupling between nodes and their distillable surrounding local subgraph. Consequently, we present Graph Resonance-fostering Network (GRN) to foster this resonance via learning node representations from their distilled resonating subgraphs. By capturing the edge-transmitted signals within this subgraph and integrating them with the node signal, GRN embeds these combined signals into the central node's representation. This node-wise embedding approach allows for generalization to unseen nodes. We validate our theoretical findings with experiments, and demonstrate that GRN generalizes robustness to unseen nodes, whilst maintaining state-of-the-art classification accuracy on perturbed graphs. Appendices can be found on arXiv version: https://arxiv.org/abs/2312.08651

NeurIPS Conference 2024 Conference Paper

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

• Zhehao Huang
• Xinwen Cheng
• JingHao Zheng
• Haoran Wang
• Zhengbao He
• Tao Li
• Xiaolin Huang

Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest descent direction, minimizing the output Kullback-Leibler divergence to exact MU inside a parameters' neighborhood. This probed direction decomposes into three components: weighted forgetting gradient ascent, fine-tuning retaining gradient descent, and a weight saliency matrix. Such decomposition derived from Euclidean metric encompasses most existing gradient-based MU methods. Nevertheless, adhering to Euclidean space may result in sub-optimal iterative trajectories due to the overlooked geometric structure of the output probability space. We suggest embedding the unlearning update into a manifold rendered by the remaining geometry, incorporating second-order Hessian from the remaining data. It helps prevent effective unlearning from interfering with the retained performance. However, computing the second-order Hessian for large-scale models is intractable. To efficiently leverage the benefits of Hessian modulation, we propose a fast-slow parameter update strategy to implicitly approximate the up-to-date salient unlearning direction. Free from specific modal constraints, our approach is adaptable across computer vision unlearning tasks, including classification and generation. Extensive experiments validate our efficacy and efficiency. Notably, our method successfully performs class-forgetting on ImageNet using DiT and forgets a class on CIFAR-10 using DDPM in just 50 steps, compared to thousands of steps required by previous methods. Code is available at Unified-Unlearning-w-Remain-Geometry.

EAAI Journal 2023 Journal Article

A hybrid multi-stage decision-making method with probabilistic interval-valued hesitant fuzzy set for 3D printed composite material selection

• Guoquan Xie
• Kui Wang
• Xuan Wu
• Jin Wang
• Tao Li
• Yong Peng
• Honghao Zhang

The 3D printed composite material selection is of great interest due to its extensive application prospect and can be considered as a challenging multiple-criteria decision making (MCDM) issue. The hesitation and uncertainty of experts are difficult to measure, and the high degree of interaction among criteria is often overlooked in the decision process. In addition, composites are required to serve in harsh environments for various mechanical and industrial fields, resulting in the degradation of mechanical properties. In this study, a hybrid multi-stage decision-making method is developed to conduct 3D printed composite material selection in harsh environments. The theory of probabilistic interval-valued hesitant fuzzy set (PIVHFS) is proposed to characterize the decision-making information of experts, which can effectively quantify the assessment in uncertain environments. An integrated method that combines Choquet fuzzy integral and Shapley value is proposed to obtain the weight vector of criteria, which can reflect the mutual influence between criteria and their overall importance. The final decision-making result and the optimal alternative can be calculated by the PIVHFS-based Tomada de Decisão Interativa Multicritério and Technique for order preference by similarity to an ideal solution (TODIM-TOPSIS) method. An empirical application, i. e. , 3D printed composites in the background of automotive chassis, is applied to validate the application of the proposed method. Comparative analysis, sensitivity analysis, and managerial implications are also conducted to illustrate the validity of the method. This paper provides a valuable tool for addressing the material selection issue of 3D printed composites from a multi-criteria perspective.

TMLR Journal 2023 Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

• Aarohi Srivastava
• Abhinav Rastogi
• Abhishek Rao
• Abu Awal Md Shoeb
• Abubakar Abid
• Adam Fisch
• Adam R. Brown
• Adam Santoro

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG- bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood develop- ment, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google- internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

JMLR Journal 2023 Journal Article

Importance Sparsification for Sinkhorn Algorithm

• Mengyu Li
• Jun Yu
• Tao Li
• Cheng Meng

Sinkhorn algorithm has been used pervasively to approximate the solution to optimal transport (OT) and unbalanced optimal transport (UOT) problems. However, its practical application is limited due to the high computational complexity. To alleviate the computational burden, we propose a novel importance sparsification method, called Spar-Sink, to efficiently approximate entropy-regularized OT and UOT solutions. Specifically, our method employs natural upper bounds for unknown optimal transport plans to establish effective sampling probabilities, and constructs a sparse kernel matrix to accelerate Sinkhorn iterations, reducing the computational cost of each iteration from $O(n^2)$ to $\widetilde{O}(n)$ for a sample of size $n$. Theoretically, we show the proposed estimators for the regularized OT and UOT problems are consistent under mild regularity conditions. Experiments on various synthetic data demonstrate Spar-Sink outperforms mainstream competitors in terms of both estimation error and speed. A real-world echocardiogram data analysis shows Spar-Sink can effectively estimate and visualize cardiac cycles, from which one can identify heart failure and arrhythmia. To evaluate the numerical accuracy of cardiac cycle prediction, we consider the task of predicting the end-systole time point using the end-diastole one. Results show Spar-Sink performs as well as the classical Sinkhorn algorithm, requiring significantly less computational time. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

EAAI Journal 2023 Journal Article

Small samples noise prediction of train electric traction system fan based on a multiple regression-fuzzy neural network

• Tao Li
• Xiaoting Wu
• Yuyao He
• Xuanlin Peng
• Jun Yang
• Rongjun Ding
• Caichun He

The fan noise in the train electric traction system contributes to the main noise of the train, affecting the comfort of the passengers. The prediction of fan noise can serve as a foundation for the design and fault diagnosis of the fan in the train electric traction system as well as noise reduction. This paper proposes a prediction model based on multiple regression analysis and a double-layer fuzzy neural network (MRA-2LFNN). After the multiple regression analysis of the train electric traction system fan noise is performed to determine the prediction input, a fuzzy neural network is used to predict the fan noise. Afterward, further analysis of noise influencing factors is presented based on the experimental results, and the possibility of the fan optimal design is discussed. This method can make accurate predictions using a small sample of fan noise data, reducing the need for data samples and lowering costs. The experimental results show that the proposed method can achieve better prediction results using the small sample dataset by training and verifying the actual train electric traction system fan noise data, and the average prediction accuracy rate is 94. 15%, After discussion, when the number of fan blades is 16, the train electric traction system exhibits improved noise performance.

JBHI Journal 2022 Journal Article

Inferring the Individual Psychopathologic Deficits With Structural Connectivity in a Longitudinal Cohort of Schizophrenia

• Yi Sun
• Zhe Zhang
• Ioannis Kakkos
• George K. Matsopoulos
• Jingjia Yuan
• John Suckling
• Luoyi Xu
• Shuxia Cao

The prediction of schizophrenia-related psychopathologic deficits is exceedingly important in the fields of psychiatry and clinical practice. However, objective association of the brain structure alterations to the illness clinical symptoms is challenging. Although, schizophrenia has been characterized as a brain dysconnectivity syndrome, evidence accounting for neuroanatomical network alterations remain scarce. Moreover, the absence of generalized connectome biomarkers for the assessment of illness progression further perplexes the prediction of long-term symptom severity. In this paper, a combination of individualized prediction models with quantitative graph theoretical analysis was adopted, providing a comprehensive appreciation of the extent to which the brain network properties are affected over time in schizophrenia. Specifically, Connectome-based Prediction Models were employed on Structural Connectivity (SC) features, efficiently capturing individual network-related differences, while identifying the anatomical connectivity disturbances contributing to the prediction of psychopathological deficits. Our results demonstrated distinctions among widespread cortical circuits responsible for different domains of symptoms, indicating the complex neural mechanisms underlying schizophrenia. Furthermore, the generated models were able to significantly predict changes of symptoms using SC features at follow-up, while the preserved SC features suggested an association with improved positive and overall symptoms. Moreover, cross-sectional significant deficits were observed in network efficiency and a progressive aberration of global integration in patients compared to healthy controls, representing a group-consensus pathological map, while supporting the dysconnectivity hypothesis.

AAAI Conference 2022 System Paper

PYLON: A PyTorch Framework for Learning with Constraints

• Kareem Ahmed
• Tao Li
• Thy Ton
• Quan Guo
• Kai-Wei Chang
• Parisa Kordjamshidi
• Vivek Srikumar
• Guy Van den Broeck

Deep learning excels at learning task information from large amounts of data, but struggles with learning from declarative high-level knowledge that can be more succinctly expressed directly. In this work, we introduce PYLON, a neuro-symbolic training framework that builds on PyTorch to augment procedurally trained models with declaratively specified knowledge. PYLON lets users programmatically specify constraints as Python functions and compiles them into a differentiable loss, thus training predictive models that fit the data whilst satisfying the specified constraints. PYLON includes both exact as well as approximate compilers to efficiently compute the loss, employing fuzzy logic, sampling methods, and circuits, ensuring scalability even to complex models and constraints. Crucially, a guiding principle in designing PYLON is the ease with which any existing deep learning codebase can be extended to learn from constraints in a few lines of code: a function that expresses the constraint, and a single line to compile it into a loss. Our demo comprises of models in NLP, computer vision, logical games, and knowledge graphs that can be interactively trained using constraints as supervision.

NeurIPS Conference 2021 Conference Paper

Learning Causal Semantic Representation for Out-of-Distribution Prediction

• Chang Liu
• Xinwei Sun
• Jindong Wang
• Haoyue Tang
• Tao Li
• Tao Qin
• Wei Chen
• Tie-Yan Liu

Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output. To address the problem, we propose a Causal Semantic Generative model (CSG) based on a causal reasoning so that the two factors are modeled separately, and develop methods for OOD prediction from a single training domain, which is common and challenging. The methods are based on the causal invariance principle, with a novel design in variational Bayes for both efficient learning and easy prediction. Theoretically, we prove that under certain conditions, CSG can identify the semantic factor by fitting training data, and this semantic-identification guarantees the boundedness of OOD generalization error and the success of adaptation. Empirical study shows improved OOD performance over prevailing baselines.

YNICL Journal 2020 Journal Article

Altered resting-state dynamic functional brain networks in major depressive disorder: Findings from the REST-meta-MDD consortium

• Yicheng Long
• Hengyi Cao
• Chaogan Yan
• Xiao Chen
• Le Li
• Francisco Xavier Castellanos
• Tongjian Bai
• Qijing Bo

BACKGROUND: Major depressive disorder (MDD) is known to be characterized by altered brain functional connectivity (FC) patterns. However, whether and how the features of dynamic FC would change in patients with MDD are unclear. In this study, we aimed to characterize dynamic FC in MDD using a large multi-site sample and a novel dynamic network-based approach. METHODS: Resting-state functional magnetic resonance imaging (fMRI) data were acquired from a total of 460 MDD patients and 473 healthy controls, as a part of the REST-meta-MDD consortium. Resting-state dynamic functional brain networks were constructed for each subject by a sliding-window approach. Multiple spatio-temporal features of dynamic brain networks, including temporal variability, temporal clustering and temporal efficiency, were then compared between patients and healthy subjects at both global and local levels. RESULTS: ). Corresponding local changes in MDD were mainly found in the default-mode, sensorimotor and subcortical areas. Measures of temporal variability and characteristic temporal path length were significantly correlated with depression severity in patients (corrected p < 0.05). Moreover, the observed between-group differences were robustly present in both first-episode, drug-naïve (FEDN) and non-FEDN patients. CONCLUSIONS: Our findings suggest that excessive temporal variations of brain FC, reflecting abnormal communications between large-scale bran networks over time, may underlie the neuropathology of MDD.

YNICL Journal 2020 Journal Article

Biotypes of major depressive disorder: Neuroimaging evidence from resting-state default mode network patterns

• Sugai Liang
• Wei Deng
• Xiaojing Li
• Andrew J. Greenshaw
• Qiang Wang
• Mingli Li
• Xiaohong Ma
• Tong-Jian Bai

BACKGROUND: Major depressive disorder (MDD) is heterogeneous disorder associated with aberrant functional connectivity within the default mode network (DMN). This study focused on data-driven identification and validation of potential DMN-pattern-based MDD subtypes to parse heterogeneity of the disorder. METHODS: The sample comprised 1397 participants including 690 patients with MDD and 707 healthy controls (HC) registered from multiple sites based on the REST-meta-MDD Project in China. Baseline resting-state functional magnetic resonance imaging (rs-fMRI) data was recorded for each participant. Discriminative features were selected from DMN between patients and HC. Patient subgroups were defined by K-means and principle component analysis in the multi-site datasets and validated in an independent single-site dataset. Statistical significance of resultant clustering were confirmed. Demographic and clinical variables were compared between identified patient subgroups. RESULTS: Two MDD subgroups with differing functional connectivity profiles of DMN were identified in the multi-site datasets, and relatively stable in different validation samples. The predominant dysfunctional connectivity profiles were detected among superior frontal cortex, ventral medial prefrontal cortex, posterior cingulate cortex and precuneus, whereas one subgroup exhibited increases of connectivity (hyperDMN MDD) and another subgroup showed decreases of connectivity (hypoDMN MDD). The hyperDMN subgroup in the discovery dataset had age-related severity of depressive symptoms. Patient subgroups had comparable demographic and clinical symptom variables. CONCLUSIONS: Findings suggest the existence of two neural subtypes of MDD associated with different dysfunctional DMN connectivity patterns, which may provide useful evidence for parsing heterogeneity of depression and be valuable to inform the search for personalized treatment strategies.

AAAI Conference 2020 Conference Paper

On Measuring and Mitigating Biased Inferences of Word Embeddings

• Sunipa Dev
• Tao Li
• Jeff M. Phillips
• Vivek Srikumar

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using the task of natural language inference. We demonstrate a reduction in invalid inferences via bias mitigation strategies on static word embeddings (GloVe). Further, we show that for gender bias, these techniques extend to contextualized embeddings when applied selectively only to the static components of contextualized embeddings (ELMo, BERT).

ICRA Conference 2019 Conference Paper

BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving

• Jianru Xue
• Jianwu Fang
• Tao Li
• Bohua Zhang
• Pu Zhang 0001
• Zhen Ye
• Jian Dou

In autonomous driving community, numerous benchmarks have been established to assist the tasks of 3D/2D object detection, stereo vision, semantic/instance segmentation. However, the more meaningful dynamic evolution of the surrounding objects of ego-vehicle is rarely exploited, and lacks a large-scale dataset platform. To address this, we introduce BLVD, a large-scale 5D semantics benchmark which does not concentrate on the static detection or semantic/instance segmentation tasks tackled adequately before. Instead, BLVD aims to provide a platform for the tasks of dynamic 4D (3D+temporal) tracking, 5D (4D+interactive) interactive event recognition and intention prediction. This benchmark will boost the deeper understanding of traffic scenes than ever before. We totally yield 249, 129 3D annotations, 4, 902 independent individuals for tracking with the length of overall 214, 922 points, 6, 004 valid fragments for 5D interactive event recognition, and 4, 900 individuals for 5D intention prediction. These tasks are contained in four kinds of scenarios depending on the object density (low and high) and light conditions (daytime and nighttime). The benchmark can be downloaded from our project site https://github.com/VCCIV/BLVD/.

YNICL Journal 2019 Journal Article

Low-rank network signatures in the triple network separate schizophrenia and major depressive disorder

• Wei Han
• Christian Sorg
• Changgang Zheng
• Qinli Yang
• Xiaosong Zhang
• Arvid Ternblom
• Cobbinah Bernard Mawuli
• Lianli Gao

Brain imaging studies have revealed that functional and structural brain connectivity in the so-called triple network (i.e., default mode network (DMN), salience network (SN) and central executive network (CEN)) are consistently altered in schizophrenia. However, similar changes have also been found in patients with major depressive disorder, prompting the question of specific triple network signatures for the two disorders. In this study, we proposed Supervised Convex Nonnegative Matrix Factorization (SCNMF) to extract distributed multi-modal brain patterns. These patterns distinguish schizophrenia and major depressive disorder in a latent low-dimensional space of the triple brain network. Specifically, 21 patients of schizophrenia and 25 patients of major depressive disorder were assessed by T1-weighted, diffusion-weighted, and resting-state functional MRIs. Individual structural and functional connectivity networks, based on pre-defined regions of the triple network were constructed, respectively. Afterwards, SCNMF was employed to extract the discriminative patterns. Experiments indicate that SCNMF allows extracting the low-rank discriminative patterns between the two disorders, achieving a classification accuracy of 82.6% based on the extracted functional and structural abnormalities with support vector machine. Experimental results show the specific brain patterns for schizophrenia and major depressive disorder that are multi-modal, complex, and distributed in the triple network. Parts of the prefrontal cortex including superior frontal gyri showed variation between patients with schizophrenia and major depression due to structural properties. In terms of functional properties, the middle cingulate cortex, inferior parietal lobule, and cingulate cortex were the most discriminative regions.

TIST Journal 2019 Journal Article

Using Sparse Representation to Detect Anomalies in Complex WSNs

• Xiaoming Li
• Guangquan Xu
• Xi Zheng
• Kaitai Liang
• Emmanouil Panaousis
• Tao Li
• Wei Wang
• Chao Shen

In recent years, wireless sensor networks (WSNs) have become an active area of research for monitoring physical and environmental conditions. Due to the interdependence of sensors, a functional anomaly in one sensor can cause a functional anomaly in another sensor, which can further lead to the malfunctioning of the entire sensor network. Existing research work has analysed faulty sensor anomalies but fails to show the effectiveness throughout the entire interdependent network system. In this article, a dictionary learning algorithm based on a non-negative constraint is developed, and a sparse representation anomaly node detection method for sensor networks is proposed based on the dictionary learning. Through experiment on a specific thermal power plant in China, we verify the robustness of our proposed method in detecting abnormal nodes against four state of the art approaches and proved our method is more robust. Furthermore, the experiments are conducted on the obtained abnormal nodes to prove the interdependence of multi-layer sensor networks and reveal the conditions and causes of a system crash.

EAAI Journal 2018 Journal Article

Particle swarm optimizer with crossover operation

• Yonggang Chen
• Lixiang Li
• Jinghua Xiao
• Yixian Yang
• Jun Liang
• Tao Li

A particle swarm optimization algorithm with crossover operation (PSOCO) is proposed. In the proposed PSOCO, two different crossover operations are employed in order to breed promising exemplars. By performing crossover on the personal historical best position of each particle, the effective guiding exemplars are constructed and they maintain a good diversity. In turn, these high quality exemplars are used to guide the evolution of particles. PSOCO is two-layer particle swarm optimization with positive feedback mechanism. In order to test the performance of PSOCO, we use a set of widely used benchmark functions. The experimental results demonstrate that the proposed PSOCO is a competitive optimizer in terms of both solution quality and efficiency.

TIST Journal 2016 Journal Article

CSM

• Yexi Jiang
• Chang-Shing Perng
• Anca Sailer
• Ignacio Silva-Lepe
• Yang Zhou
• Tao Li

The cloud service marketplace (CSM) is an exploratory project aiming to provide “an AppStore for Services.” It is an intelligent online marketplace that facilitates service discovery and acquisition for enterprise customers. Traditional service discovery and acquisition are time-consuming. In the era of OneClick Checkout and pay-as-you-go service plans, users expect services to be purchased online efficiently and conveniently. However, as services are complex and different from software apps, the currently prevailing App Store based on keyword search is inadequate for services. In CSM, exploring and configuring services are an iterative process. Customers provide their requirements in natural language and interact with the system through questioning and answering. Learning from the input, the system can incrementally clarify users’ intention, narrow down the candidate services, and profile the configuration information for the candidates at the same time. CSM’s back end is built around the Services Knowledge Graph (SKG) and leverages data mining technologies to enable the semantic understanding of customers’ requirements. To quantitatively assess the value of CSM, empirical evaluation on real and synthetic datasets and case studies are given to demonstrate the efficacy and effectiveness of the proposed system.

TAAS Journal 2016 Journal Article

Managing Server Clusters on Renewable Energy Mix

• Chao Li
• Rui Wang
• Depei Qian
• Tao Li

As climate change has become a global concern and server energy demand continues to soar, many IT companies have started to explore server clusters running on various renewable energy sources. Existing green data center designs often yield suboptimal performance as they only look at a certain specific type of energy source. This article explores data centers powered by hybrid renewable energy systems. We propose GreenWorks, a framework for HPC data centers running on a renewable energy mix. Specifically, GreenWorks features a cross-layer power management scheme tailored to the timing behaviors and capacity constraints of different energy sources. Using realistic workload traces and renewable energy data, we show that GreenWorks could provide a near-optimal workload performance (within 3% difference) on average. It can also reduce the worst-case performance degradation by 43% compared to the state-of-the-art design. Moreover, the performance improvements are based on carbon-neutral operations and are not at the cost of significant efficiency degradation and reduced battery lifecycle. Our technique becomes more efficient when servers become more energy proportional and can effectively handle the ever-increasing depth of renewable power penetration in green data centers.

TIST Journal 2015 Journal Article

Soter

• Yanfang Ye
• Tao Li
• Haiyin Shen

In recent years, crimes against children and cases of missing children have increased at a high rate. Therefore, there is an urgent need for safety support systems to prevent crimes against children or for antiloss, especially when parents are not with their children, such as to and from school. However, existing children’s tracking systems are not smart enough to provide the safety supports, as they simply locate the children’s positions without offering any notification to parents that their children may be in danger. In addition, there is limited research on children’s tracking and their antiloss. In this article, based on location histories, we introduce novel notions of children’s life patterns that capture their general lifestyles and regularities, and develop an intelligent data mining framework to learn the safe regions and safe routes of children on the cloud side. When the children may be in danger, their parents will receive automatic notifications from the cloud. We also propose an effective energy-efficient positioning scheme that leverages the location tracking accuracy of the children while keeping energy overhead low by using a hybrid global positioning system and a global system for mobile communications. To the best of our knowledge, this is the first attempt in applying data mining techniques to applications designed for children’s safety. Our proposed techniques have been incorporated into Soter, a children’s safeguard system that is used to provide cloud service for smart bracelets produced by Qihoo. The case studies on real smart bracelet users of Qihoo demonstrate the effectiveness of our proposed methods and Soter for children’s safety.

TIST Journal 2015 Journal Article

TerraFly GeoCloud

• Mingjin Zhang
• Huibo Wang
• Yun Lu
• Tao Li
• Yudong Guang
• Chang Liu
• Erik Edrosa
• Hongtai Li

With the exponential growth of the usage of web map services, geo-data analysis has become more and more popular. This article develops an online spatial data analysis and visualization system, TerraFly GeoCloud, which helps end-users visualize and analyze spatial data and share the analysis results. Built on the TerraFly Geo spatial database, TerraFly GeoCloud is an extra layer running upon the TerraFly map and can efficiently support many different visualization functions and spatial data analysis models. Furthermore, users can create unique URLs to visualize and share the analysis results. TerraFly GeoCloud also enables the MapQL technology to customize map visualization using SQL-like statements. The system is available at http://terrafly.fiu.edu/GeoCloud/.

YNIMG Journal 2013 Journal Article

Mapping thalamocortical networks in rat brain using resting-state functional connectivity

• Zhifeng Liang
• Tao Li
• Jean King
• Nanyin Zhang

Thalamocortical connectivity plays a vital role in brain function. The anatomy and function of thalamocortical networks have been extensively studied in animals by numerous invasive techniques. Non-invasively mapping thalamocortical networks in humans has also been demonstrated by utilizing resting-state functional magnetic resonance imaging (rsfMRI). However, success in simultaneously imaging multiple thalamocortical networks in animals is rather limited. This is largely due to the profound impact of anesthesia used in most animal experiments on functional connectivity measurement. Here we have employed an awake animal imaging approach to systematically map thalamocortical connectivity for multiple thalamic nuclei in rats. Seed-based correlational analysis demonstrated robust functional connectivity for each thalamic nucleus in the cortex, and the cortical connectivity profiles revealed were in excellent accordance with the known thalamocortical anatomical connections. In addition, partial correlation analysis was utilized to further improve the spatial specificity of thalamocortical connectivity. Taken together, these findings have provided important evidence supporting the validity of rsfMRI measurement in awake animals. More importantly, the present study has made it possible to non-invasively investigate the function, neuroplasticity and mutual interactions of thalamocortical networks in animal models.

ICRA Conference 2013 Conference Paper

Online learning for behavior switching in a soft robotic arm

• Tao Li
• Kohei Nakajima
• Rolf Pfeifer

Soft robots possess several potential advantages over traditional articulated ones and have attracted significant interest in recent years. However, to control this new type of robots using conventional model-based robotic control approaches is generally ineffective. In this paper, we investigate the challenge to embed and switch among multiple behaviors for an octopus-inspired soft robotic arm. An online learning method for reservoir computing is exploited for this task. This online learning method does not require a separate teaching data collection phase; thus, it has the potential to achieve autonomy in soft robots. Our result shows the feasibility of this approach.

ICRA Conference 2012 Conference Paper

Behavior switching using reservoir computing for a soft robotic arm

• Tao Li
• Kohei Nakajima
• Matteo Cianchetti
• Cecilia Laschi
• Rolf Pfeifer

Soft robots have significant advantages over traditional robots made of rigid materials. However, controlling this type of robot by conventional approaches is difficult. Reservoir computing has been demonstrated to be an effective approach for achieving rapid learning in benchmark tasks and conventional robots. In this study, we investigated the feasibility and capacity of the reservoir computing approach to embedding and switching between multiple behaviors in a on-line manner in a soft robotic arm. The result shows that this approach can successfully achieve this task.

TIST Journal 2012 Journal Article

DClusterE

• Yi Zhang
• Tao Li

Over the last decade, document clustering, as one of the key tasks in information organization and navigation, has been widely studied. Many algorithms have been developed for addressing various challenges in document clustering and for improving clustering performance. However, relatively few research efforts have been reported on evaluating and understanding document clustering results. In this article, we present DClusterE, a comprehensive and effective framework for document clustering evaluation and understanding using information visualization. DClusterE integrates cluster validation with user interactions and offers rich visualization tools for users to examine document clustering results from multiple perspectives. In particular, through informative views including force-directed layout view, matrix view, and cluster view, DClusterE provides not only different aspects of document inter/intra-clustering structures, but also the corresponding relationship between clustering results and the ground truth. Additionally, DClusterE supports general user interactions such as zoom in/out, browsing, and interactive access of the documents at different levels. Two new techniques are proposed to implement DClusterE: (1) A novel multiplicative update algorithm (MUA) for matrix reordering to generate narrow-banded (or clustered) nonzero patterns from documents. Combined with coarse seriation, MUA is able to provide better visualization of the cluster structures. (2) A Mallows-distance-based algorithm for establishing the relationship between the clustering results and the ground truth, which serves as the basis for coloring schemes. Experiments and user studies are conducted to demonstrate the effectiveness and efficiency of DClusterE.

AAAI Conference 2012 Conference Paper

Generating Pictorial Storylines Via Minimum-Weight Connected Dominating Set Approximation in Multi-View Graphs

• Dingding Wang
• Tao Li
• Mitsunori Ogihara

This paper introduces a novel framework for generating pictorial storylines for given topics from text and image data on the Internet. Unlike traditional text summarization and timeline generation systems, the proposed framework combines text and image analysis and delivers a storyline containing textual, pictorial, and structural information to provide a sketch of the topic evolution. A key idea in the framework is the use of an approximate solution for the dominating set problem. Given a collection of topic-related objects consisting of images and their text descriptions, a weighted multi-view graph is first constructed to capture the contextual and temporal relationships among these objects. Then the objects are selected by solving the minimum-weighted connected dominating set problem defined on this graph. Comprehensive experiments on real-world data sets demonstrate the effectiveness of the proposed framework.

TIST Journal 2012 Journal Article

Mining the “Voice of the Customer” for Business Prioritization

• Wei Peng
• Tong Sun
• Shriram Revankar
• Tao Li

To gain competitiveness and sustained growth in the 21st century, most businesses are on a mission to become more customer-centric. In order to succeed in this endeavor, it is crucial not only to synthesize and analyze the VOC (the VO ice of the C ustomer) data (i.e., the feedbacks or requirements raised by customers), but also to quickly turn these data into actionable knowledge. Although there are many technologies being developed in this complex problem space, most existing approaches in analyzing customer requests are ad hoc, time-consuming, error-prone, people-based processes which hardly scale well as the quantity of customer information explodes. This often results in the slow response to customer requests. In this article, in order to mine VOC to extract useful knowledge for the best product or service quality, we develop a hybrid framework that integrates domain knowledge with data-driven approaches to analyze the semi-structured customer requests. The framework consists of capturing functional features, discovering the overlap or correlation among the features, and identifying the evolving feature trend by using the knowledge transformation model. In addition, since understanding the relative importance of the individual customer request is very critical and has a direct impact on the effective prioritization in the development process, we develop a novel semantic enhanced link-based ranking (SELRank) algorithm for relatively rating/ranking both customer requests and products. The framework has been successfully applied on Xerox Office Group Feature Enhancement Requirements (XOG FER) datasets to analyze customer requests.

AAAI Conference 2011 Conference Paper

Integrating Clustering and Multi-Document Summarization by Bi-Mixture Probabilistic Latent Semantic Analysis (PLSA) with Sentence Bases

• Chao Shen
• Tao Li
• Chris Ding

Probabilistic Latent Semantic Analysis (PLSA) has been popularly used in document analysis. However, as it is currently formulated, PLSA strictly requires the number of word latent classes to be equal to the number of document latent classes. In this paper, we propose Bi-mixture PLSA, a new formulation of PLSA that allows the number of latent word classes to be different from the number of latent document classes. We further extend Bi-mixture PLSA to incorporate the sentence information, and propose Bi-mixture PLSA with sentence bases (Bi-PLSAS) to simultaneously cluster and summarize the documents utilizing the mutual influence of the document clustering and summarization procedures. Experiments on real-world datasets demonstrate the effectiveness of our proposed methods.

YNIMG Journal 2010 Journal Article

Localization of cerebral functional deficits in treatment-naive, first-episode schizophrenia using resting-state fMRI

• Xiao-Qi Huang
• Su Lui
• Wei Deng
• Raymond C.K. Chan
• Qi-Zhu Wu
• Li-Jun Jiang
• Jun-Ran Zhang
• Zhi-Yun Jia

Background Spontaneous low-frequency fluctuations (LFF) in the blood oxygen level-dependent (BOLD) functional magnetic resonance imaging (fMRI) signal have been shown to reflect cerebral spontaneous neural activity, and the present study attempts to explore the functional changes in the regional brain in patients with schizophrenia using the amplitude of the BOLD signals. Methods A total of 66 treatment-naïve, first-episode schizophrenia (FES) patients and 66 normal age- and sex-matched controls were recruited. Resting-state fMRIs were obtained using a gradient-echo echo-planar imaging sequence. The amplitude of LFF (ALFF) was calculated using REST software. Voxel-based analysis of the ALFF maps between control and patient groups was performed with twos-sample t-tests using SPM2. Results Compared to the controls, the FES group showed significantly decreased ALFF in the medial prefrontal lobe (MPFC) and significant increases in the ALFF in the left and right putamen. Significant positive correlations were observed between ALFF values in the bilateral putamen in both the patient and control groups. Conclusions Alterations of the ALFF in the MPFC and putamen in FES observed in the present study suggest that the functional abnormalities of those areas are at an early stage of the disease.

IJCAI Conference 2009 Conference Paper

• Fei Wang
• Xin Wang
• Tao Li

Clustering aggregation has emerged as an important extension of the classical clustering problem. It refers to the situation in which a number of different (input) clusterings have been obtained for a particular data set and it is desired to aggregate those clustering results to get a better clustering solution. In this paper, we propose a unified framework to solve the clustering aggregation problem, where the aggregated clustering result is obtained by minimizing the (weighted) sum of the Bregman divergence between it and all the input clusterings. Moreover, under our algorithm framework, we also propose a novel cluster aggregation problem where some must-link and cannot-link constraints are given in addition to the input clusterings. Finally the experimental results on some real world data sets are presented to show the effectiveness of our method.

IJCAI Conference 2009 Conference Paper

• Dan Zhang
• Fei Wang
• Luo Si
• Tao Li

Clustering, classification, and regression, are three major research topics in machine learning. So far, much work has been conducted in solving multiple instance classification and multiple instance regression problems, where supervised training patterns are given as bags and each bag consists of some instances. But the research on unsupervised multiple instance clustering is still limited. This paper formulates a novel Maximum Margin Multiple Instance Clustering (M3 IC) problem for the multiple instance clustering task. To avoid solving a nonconvex optimization problem directly, M3 IC is further relaxed, which enables an efficient optimization solution with a combination of Constrained Concave-Convex Procedure (CCCP) and the Cutting Plane method. Furthermore, this paper analyzes some important properties of the proposed method and the relationship between the proposed method and some other related ones. An extensive set of empirical results demonstrate the advantages of the proposed method against existing research for both effectiveness and efficiency.

IJCAI Conference 2009 Conference Paper

• Fei Wang
• Bin Zhang
• Ta-Hsin Li
• Wen Jun Yin
• Jin Dong
• Tao Li

In this paper, we consider a general problem of semi-supervised preference learning, in which we assume that we have the information of the extreme cases and some ordered constraints, our goal is to learn the unknown preferences of the other places. Taking the potential housing place selection problem as an example, we have many candidate places together with their associated information (e. g. , position, environment), and we know some extreme examples (i. e. several places are perfect for building a house, and several places are the worst that cannot build a house there), and we know some partially ordered constraints (i. e. for two places, which place is better), then how can we judge the preference of one potential place whose preference is unknown beforehand? We propose a Bayesian framework based on Gaussian process to tackle this problem, from which we not only solve for the unknown preferences, but also the hyperparameters contained in our model.

EAAI Journal 2006 Journal Article

Output feedback control for uncertain discrete-time hyperbolic fuzzy systems

• Shaosheng Zhou
• Tao Li
• Hanyong Shao
• Wei Xin Zheng

The paper deals with the problem of output feedback H ∞ control for a class of uncertain discrete-time fuzzy systems with hyperbolic models. The hyperbolic model can be obtained from a set of linguistic rules. The uncertainties in the systems under consideration are assumed to be of linear fractional form, which includes the norm-bounded uncertainty as a special case and can describe a class of rational nonlinearities. A sufficient condition for robust stability with H ∞ norm bound of the hyperbolic system is obtained in terms of a linear matrix inequality (LMI). Moreover, an output feedback controller can be constructed to guarantee the closed-loop system being robustly stable with H ∞ norm bound. Finally, a numerical example is given to demonstrate the applicability of the proposed approach.