Author name cluster

Jing Tao

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

13 papers

2 author rows

EAAI Journal 2026 Journal Article

The research on the diagnostic technology for aortic dissection and acute myocardial infarction based on Raman and infrared spectroscopy combined with multimodal deep learning

Lei Yan
Guangyao Ma
Cheng Chen
Chen Chen
Jing Tao
Xuguang Zhou
Ting Tian
Hao Liu

Background Aortic dissection and myocardial infarction are two common and life-threatening cardiovascular emergencies characterized by sudden onset, high mortality, and overlapping clinical symptoms such as chest pain and respiratory distress, which make accurate and timely clinical differentiation particularly challenging. Current mainstream diagnostic techniques, including computed tomography and transesophageal echocardiography, provide valuable anatomical and functional information but are often costly, time-consuming, and insensitive to early-stage biochemical alterations, which may result in missed or incorrect diagnoses in emergency settings. Aortic dissection often requires immediate repair of the damaged vessel to prevent further expansion or rupture, whereas myocardial infarction requires rapid restoration of blood flow to the myocardium. The treatment approaches for the two conditions are distinct, and misdiagnosis can result in severe consequences. Therefore, more convenient, rapid, and efficient diagnostic methods are urgently needed. Methods Vibrational spectroscopy is a noninvasive analytical technique with high sensitivity to molecular and biochemical changes in biological samples, and Raman spectroscopy and infrared spectroscopy target distinct molecular vibrational modes, providing complementary pathological information. In this study, a multimodal attention fusion network was developed to integrate Raman spectroscopy and infrared spectroscopy data for rapid disease classification. Results Experimental results demonstrated that the proposed method achieved a diagnostic accuracy of 94. 06 % and a specificity of 97. 03 % percent in distinguishing aortic dissection, myocardial infarction, and non-critical cases. Conclusion This method provides an innovative and efficient decision-support tool for the clinical differentiation of aortic dissection and myocardial infarction, offering significant clinical value.

Details DOI

AAAI Conference 2025 Conference Paper

Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models

Jie Ma
Zhitao Gao
Qi Chai
Wangchun Sun
Pinghui Wang
Hongbin Pei
Jing Tao
Lingyun Song

Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. In contrast, knowledge graphs encompass extensive, multi-relational structures that store a vast array of symbolic facts. Consequently, integrating LLMs with knowledge graphs has been extensively explored, with Knowledge Graph Question Answering (KGQA) serving as a critical touchstone for the integration. This task requires LLMs to answer natural language questions by retrieving relevant triples from knowledge graphs. However, existing methods face two significant challenges: *excessively long reasoning paths distracting from the answer generation*, and *false-positive relations hindering the path refinement*. In this paper, we propose an iterative interactive KGQA framework that leverages the interactive learning capabilities of LLMs to perform reasoning and Debating over Graphs (DoG). Specifically, DoG employs a subgraph-focusing mechanism, allowing LLMs to perform answer trying after each reasoning step, thereby mitigating the impact of lengthy reasoning paths. On the other hand, DoG utilizes a multi-role debate team to gradually simplify complex questions, reducing the influence of false-positive relations. This debate mechanism ensures the reliability of the reasoning process. Experimental results on five public datasets demonstrate the effectiveness and superiority of our architecture. Notably, DoG outperforms the state-of-the-art method ToG by 23.7% and 9.1% in accuracy on WebQuestions and GrailQA, respectively. Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

Jie Ma
NING QU
Zhitao Gao
Xing Rui
Jun Liu
Hongbin Pei
Jiang Xie
Lingyun Song

Knowledge graph-based retrieval-augmented generation seeks to mitigate hallucinations in Large Language Models (LLMs) caused by insufficient or outdated knowledge. However, existing methods often fail to fully exploit the prior knowledge embedded in knowledge graphs (KGs), particularly their structural information and explicit or implicit constraints. The former can enhance the faithfulness of LLMs' reasoning, while the latter can improve the reliability of response generations. Motivated by these, we propose a trustworthy reasoning framework, termed Deliberation over Priors (\texttt{DP}), which sufficiently utilizes the priors contained in KGs. Specifically, \texttt{DP} adopts a progressive knowledge distillation strategy that integrates structural priors into LLMs through a combination of supervised fine-tuning and Kahneman-Tversky Optimization, thereby improving the faithfulness of relation path generation. Furthermore, our framework employs a reasoning-introspection strategy, which guides LLMs to perform refined reasoning verification based on extracted constraint priors, ensuring the reliability of response generation. Extensive experiments on three benchmark datasets demonstrate that \texttt{DP} achieves new state-of-the-art performance, especially a H@1 improvement of 13% on the ComplexWebQuestions dataset, and generates highly trustworthy responses. We also conduct various analyses to verify its flexibility and practicality. Code is available at https: //github. com/mira-ai-lab/Deliberation-on-Priors.

PDF Details

ICML Conference 2025 Conference Paper

Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics

Hongbin Pei
Jingxin Hai
Yu Li
Huiqi Deng
Denghao Ma
Jie Ma 0001
Pinghui Wang
Jing Tao

Pseudo-labeling is a widely used strategy in semi-supervised learning. Existing methods typically select predicted labels with high confidence scores and high training stationarity, as pseudo-labels to augment training sets. In contrast, this paper explores the pseudo-labeling potential of predicted labels that do not exhibit these characteristics. We discover a new type of predicted labels suitable for pseudo-labeling, termed two-phase labels, which exhibit a two-phase pattern during training: they are initially predicted as one category in early training stages and switch to another category in subsequent epochs. Case studies show the two-phase labels are informative for decision boundaries. To effectively identify the two-phase labels, we design a 2- phasic metric that mathematically characterizes their spatial and temporal patterns. Furthermore, we propose a loss function tailored for two-phase pseudo-labeling learning, allowing models not only to learn correct correlations but also to eliminate false ones. Extensive experiments on eight datasets show that our proposed 2- phasic metric acts as a powerful booster for existing pseudo-labeling methods by additionally incorporating the two-phase labels, achieving an average classification accuracy gain of 1. 73% on image datasets and 1. 92% on graph datasets.

Details

AAAI Conference 2024 Conference Paper

HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning

Hongbin Pei
Taile Chen
Chen A
Huiqi Deng
Jing Tao
Pinghui Wang
Xiaohong Guan

Molecular representation learning has emerged as a game-changer at the intersection of AI and chemistry, with great potential in applications such as drug design and materials discovery. A substantial obstacle in successfully applying molecular representation learning is the difficulty of effectively and completely characterizing and learning molecular geometry, which has not been well addressed to date. To overcome this challenge, we propose a novel framework that features a novel geometric graph, termed HAGO-Graph, and a specifically designed geometric graph learning model, HAGO-Net. In the framework, the foundation is HAGO-Graph, which enables a complete characterization of molecular geometry in a hierarchical manner. Specifically, we leverage the concept of n-body in physics to characterize geometric patterns at multiple spatial scales. We then specifically design a message passing scheme, HAGO-MPS, and implement the scheme as a geometric graph neural network, HAGO-Net, to effectively learn the representation of HAGO-Graph by horizontal and vertical aggregation. We further prove DHAGO-Net, the derivative function of HAGO-Net, is an equivariant model. The proposed models are validated by extensive comparisons on four challenging benchmarks. Notably, the models exhibited state-of-the-art performance in molecular chirality identification and property prediction, achieving state-of-the-art performance on five properties of QM9 dataset. The models also achieved competitive results on molecular dynamics prediction task.

PDF Details DOI

ICML Conference 2024 Conference Paper

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing

Hongbin Pei
Yu Li
Huiqi Deng
Jingxin Hai
Pinghui Wang
Jie Ma 0001
Jing Tao
Yuheng Xiong

The advancement toward deeper graph neural networks is currently obscured by two inherent issues in message passing, oversmoothing and oversquashing. We identify the root cause of these issues as information loss due to heterophily mixing in aggregation, where messages of diverse category semantics are mixed. We propose a novel multi-track graph convolutional network to address oversmoothing and oversquashing effectively. Our basic idea is intuitive: if messages are separated and independently propagated according to their category semantics, heterophilic mixing can be prevented. Consequently, we present a novel multi-track message passing scheme capable of preventing heterophilic mixing, enhancing long-distance information flow, and improving separation condition. Empirical validations show that our model achieved state-of-the-art performance on several graph datasets and effectively tackled oversmoothing and oversquashing, setting a new benchmark of $86. 4$% accuracy on Cora.

Details

AAAI Conference 2023 Conference Paper

Multi-Action Dialog Policy Learning from Logged User Feedback

Shuo Zhang
Junzhou Zhao
Pinghui Wang
Tianxiang Wang
Zi Liang
Jing Tao
Yi Huang
Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

PDF Details DOI

YNICL Journal 2022 Journal Article

Aberrant functional metastability and structural connectivity are associated with rumination in individuals with major depressive disorder

Ruibin Zhang
Sammi-Kenzie T.S. Tam
Nichol M.L. Wong
Jingsong Wu
Jing Tao
Lidian Chen
Kangguang Lin
Tatia M.C. Lee

Rumination is a repetitive and compulsive thinking focusing on oneself, and the nature and consequences of distress. It is a core characteristic in psychiatric disorders characterized by affective dysregulation, and emerging evidence suggests that rumination is associated with aberrant dynamic functional connectivity and structural connectivity. However, the underlying neural mechanisms remain poorly understood. Here, we adopted a multimodal approach and tested the hypothesis that white matter connectivity forms the basis of the implications of temporal dynamics of functional connectivity in the rumination trait. Fifty-three depressed and ruminative individuals and a control group of 47 age- and gender-matched individuals with low levels of rumination underwent resting-state fMRI and diffusion tensor imaging. We found that lower global metastability and higher global synchrony of the dynamic functional connectivity were associated with higher levels of rumination. Specifically, the altered global synchrony and global metastability mediated the association between white matter integrity of the genu of the corpus callosum to rumination. Hence, our findings offered the first line of evidence for the intricate role of (sub)optimal transition of functional brain states in the connection of structural brain connectivity in ruminative thinking.

Details DOI

YNIMG Journal 2021 Journal Article

Fronto-cerebellar connectivity mediating cognitive processing speed

Clive H.Y. Wong
Jiao Liu
Tatia M.C. Lee
Jing Tao
Alex W.K. Wong
Bolton K.H. Chau
Lidian Chen
Chetwyn C.H. Chan

Processing speed is an important construct in understanding cognition. This study was aimed to control task specificity for understanding the neural mechanisms underlying cognitive processing speed. Forty young adult subjects performed attention tasks of two modalities (auditory and visual) and two levels of task rules (compatible and incompatible). Block-design fMRI captured BOLD signals during the tasks. Thirteen regions of interest were defined with reference to publicly available activation maps for processing speed tasks. Cognitive speed was derived from task reaction times, which yielded six sets of connectivity measures. Mixed-effect LASSO regression revealed six significant paths suggestive of a cerebello-frontal network predicting the cognitive speed. Among them, three are long range (two fronto-cerebellar, one cerebello-frontal), and three are short range (fronto-frontal, cerebello-cerebellar, and cerebello-thalamic). The long-range connections are likely to relate to cognitive control, and the short-range connections relate to rule-based stimulus-response processes. The revealed neural network suggests that automaticity, acting on the task rules and interplaying with effortful top-down attentional control, accounts for cognitive speed.

Details DOI

NeurIPS Conference 2020 Conference Paper

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

Lin Lan
Pinghui Wang
Xuefeng Du
Kaikai Song
Jing Tao
Xiaohong Guan

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users in online social networks. To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} provides each node a latent representation according to the graph structure. (2) A \emph{meta-learning module} captures the relationships between the graph structure and the node labels as prior knowledge in a meta-learning manner. Additionally, we introduce an \emph{embedding transformation function} that remedies the deficiency of the straightforward use of meta-learning. Inherently, the meta-learned prior knowledge can be used to facilitate the learning of few-shot novel labels. (3) An \emph{optimization module} employs a simple yet effective scheduling strategy to train the above two modules with a balance between graph structure learning and meta-learning. Experiments on four real-world datasets show that MetaTNE brings a huge improvement over the state-of-the-art methods.

PDF Details

YNICL Journal 2019 Journal Article

Mind-body exercise improves cognitive function and modulates the function and structure of the hippocampus and anterior cingulate cortex in patients with mild cognitive impairment

Jing Tao
Jiao Liu
Xiangli Chen
Rui Xia
Moyi Li
Maomao Huang
Shuzhen Li
Joel Park

Mild cognitive impairment (MCI) is a common neurological disorder. This study aims to investigate the modulation effect of Baduanjin (a popular mind-body exercise) on MCI. 69 patients were randomized to Baduanjin, brisk walking, or an education control group for 24 weeks. The Montreal Cognitive Assessment (MoCA) and Magnetic Resonance Imaging scans were applied at baseline and at the end of the experiment. Compared to the brisk walking and control groups, the Baduanjin group experienced significantly increased MoCA scores. Amplitude of low-frequency fluctuations (ALFF) analysis showed significantly decreased ALFF values in the right hippocampus (classic low-freqency band, 0.01-0.08 Hz) in the Baduanjin group compared to the brisk walking group and increased ALFF values in the bilateral anterior cingulate cortex (ACC, slow-5 band, 0.01-0.027 Hz) in the Baduanjin group compared to the control group. Further, ALFF value changes in the right hippocampus and bilateral ACC were significantly associated with corresponding MoCA score changes across all groups. We also found increased gray matter volume in the Baduanjin group in the right hippocampus compared to the brisk walking group and in the bilateral ACC compared to the control group. In addition, there was an increased resting state functional connectivity between the hippocampus and right angular gyrus in the Baduanjin group compared to the control group. Our results demonstrate the potential of Baduanjin for the treatment of MCI.

Details DOI

IJCAI Conference 2019 Conference Paper

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

Nuo Xu
Pinghui Wang
Long Chen
Jing Tao
Junzhou Zhao

Predicting interactions between structured entities lies at the core of numerous tasks such as drug regimen and new material design. In recent years, graph neural networks have become attractive. They represent structured entities as graphs, and then extract features from each individual graph using graph convolution operations. However, these methods have some limitations: i) their networks only extract features from a fix-sized subgraph structure (i. e. , a fix-sized receptive field) of each node, and ignore features in substructures of different sizes, and ii) features are extracted by considering each entity independently, which may not effectively reflect the interaction between two entities. To resolve these problems, we present {\em MR-GNN}, an end-to-end graph neural network with the following features: i) it uses a multi-resolution based architecture to extract node features from different neighborhoods of each node, and, ii) it uses dual graph-state long short-term memory networks (LSTMs) to summarize local features of each graph and extracts the interaction features between pairwise graphs. Experiments conducted on real-world datasets show that MR-GNN improves the prediction of state-of-the-art methods.

PDF Details

YNICL Journal 2018 Journal Article

Neurodevelopmental changes in the relationship between stress perception and prefrontal-amygdala functional circuitry

Jingsong Wu
Xiujuan Geng
Robin Shao
Nichol M.L. Wong
Jing Tao
Lidian Chen
Chetwyn C.H. Chan
Tatia M.C. Lee

Our brain during distinct developmental phases may show differential responses to perceived psychological stress, yet existing research specifically examining neurodevelopmental changes in stress processing is scarce. To fill in this research gap, this functional magnetic resonance imaging (fMRI) study examined the relationship between perceived stress and resting-state neural connectivity patterns among 67 healthy volunteers belonging to three age groups (adolescents, young adults and adults), who were supposed to be at separate neurodevelopmental phases and exhibit different affect regulatory processes in the brain. While the groups showed no significant difference in self-reported general perceived stress levels, the functional connectivity between amygdala and ventromedial prefrontal cortex (vmPFC) was positively and negatively correlated with perceived stress in adolescents and young adults respectively, while no significant correlations were observed in adults. Furthermore, among adolescents, the causal functional interaction between amygdala and vmPFC exhibited bottom-up connectivity, and that between amygdala and subgenual anterior cingulate cortex exhibited top-down connectivity, both of which changed to bilateral directions, i.e. both bottom-up and top-down connections, in both young adults and adults, supporting the notion that the amygdala and prefrontal cortical circuitries undergo functional reorganizations during brain development. These novel findings have important clinical implications in treating stress-related affective disorders in young individuals.

Details DOI