Publications

Preprint

1. Predicting stress field evolution in polycrystals with a spatio-temporal adaptive graph neural network

   Yun Bai, Wei Luo, Kaixuan Chen, Jie Song, Shunyu Liu, Xinyu Yang, Mingli Song, Yuefei Zhang, Ze Zhang

   International Journal of Plasticity, Under Review.

2. Manipulating interfacial tension and viscoelasticity of droplets with superparamagnetic nanoparticles: role of magnetic dipole interactions

   Qi Lou, Yuqing Wu, Kaixuan Chen, Shijie Qin, Xiaoping Ouyang, Dazhuan Wu

   Journal of Colloid and Interface Science, Under Review.

2025

1. From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

   Jie Yang, Yuwen Wang, Kaixuan Chen, Tongya Zheng, Yihe Zhou, Zhenbang Xiao, Ji Cao, Shunyu Liu, Mingli Song

   International Conference on Learning Representations (ICLR), 2025. [Paper]

2. Spatial-Temporal Reconstruction Error for AIGC-based Forgery Image Detection

   Chengji Shen, Zhenjiang Liu, Kaixuan Chen, Jie Lei, Mingli Song, Zunlei Feng

   IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025.

3. Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location

   Na Yu, Yutong Deng, Shunyu Liu, Kaixuan Chen, Tongya Zheng, Mingli Song

   AAAI Conference on Artificial Intelligence (AAAI), 2025.

4. Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

   Yihe Zhou, Yuxuan Zheng, Yue Hu, Kaixuan Chen, Tongya Zheng, Jie Song, Mingli Song, Shunyu Liu

   AAAI Conference on Artificial Intelligence (AAAI), 2025.

5. Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

   Waoquan Wei, Shunyu Liu, Jie Song, Tongya Zheng, Kaixuan Chen, Mingli Song

   AAAI Conference on Artificial Intelligence (AAAI), 2025.

6. Powerformer: A Section-adaptive Transformer for Power Flow Adjustment

   Kaixuan Chen, Wei Luo, Shunyu Liu, Yanquan Wei, Yihe Zhou, Yunpeng Qing, Quan Zhang, Jie Song, Mingli Song

   ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025. [Paper] [Code]

2024

1. A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective

   Yunpeng Qing, Shunyu Liu, Jingyuan Cong, Kaixuan Chen, Yihe Zhou, Mingli Song

   Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. [Paper] [Code]

2. Unified Mask Graph Modeling for Incomplete Tabular Learning

   Na Yu, Tongya Zheng, Kaixuan Chen, Shunyu Liu, Mingli Song

   International Conference on Neural Information Processing (ICONIP), 2024.

3. Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentation

   Wenda Li, Kaixuan Chen, Shunyu Liu, Tongya Zheng, Wenjie Huang, Mingli Song

   European Conference on Artificial Intelligence (ECAI), 2024. [Paper] [Code]

4. Spatiotemporal-augmented graph neural networks for human mobility simulation

   Yu Wang, Tongya Zheng, Shunyu Liu, Zunlei Feng, Kaixuan Chen, Yunzhi Hao, Mingli Song

   IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024. [Paper] [Code]

5. Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks

   Yuwen Wang, Shunyu Liu, Tongya Zheng, Kaixuan Chen, Mingli Song

   ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024. [Paper] [Code]

6. Interaction pattern disentangling for multi-agent reinforcement learning

   Shunyu Liu, Jie Song, Yihe Zhou, Na Yu, Kaixuan Chen, Zunlei Feng, Mingli Song

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. [Paper] [Code]

7. Multi-Channel Graph Fusion Representation for Tabular Data Imputation

   Na Yu, Ke Xu, Kaixuan Chen, Shunyu Liu, Tongya Zheng, Mingli Song

   International Joint Conference on Neural Networks (IJCNN), 2024. [Paper]

2023

1. Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket

   Yuwen Wang, Shunyu Liu, Kaixuan Chen, Tongtian Zhu, Ji Qiao, Mengjie Shi, Yuanyu Wan, Mingli Song

   European Conference on Artificial Intelligence (ECAI), 2023. [Paper] [Code]

2. Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework

   Shunyu Liu, Kaixuan Chen, Na Yu, Jie Song, Zunlei Feng, Mingli Song

   IEEE Transactions on Systems, Man and Cybernetics: Systems (TSMC), 2023. [Paper] [Code]

3. Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution

   Shunyu Liu, Wei Luo, Yanzhen Zhou, Kaixuan Chen, Quan Zhang, Huating Xu, Qinglai Guo, Mingli Song

   IEEE Transactions on Power Systems (TPS), 2023. [Paper] [Code]

4. Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization

   Kaixuan Chen, Shunyu Liu, Tongtian Zhu, Tongya Zheng, Haofei Zhang, Zunlei Feng, Jingwen Ye, Mingli Song

   ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023. [Paper] [Code]

5. Decentralized SGD and Average-direction SAM are Asymptotically Equivalent

   Tongtian Zhu, Fengxiang He, Kaixuan Chen, Mingli Song, Dacheng Tao

   International Conference on Machine Learning (ICML), 2023. [Paper] [Code]

6. Schema Inference for Interpretable Image Classification

   Haofei Zhang, Mengqi Xue, Xiaokang Liu, Kaixuan Chen, Jie Song, Mingli Song

   International Conference on Learning Representations (ICLR), 2023. [Paper] [Code]

7. Message-passing selection: Towards interpretable GNNs for graph classification

   Wenda Li, Kaixuan Chen, Shunyu Liu, Wenjia Huang, Haofei Zhang, Yingjie Tian, Yun Su, Mingli Song

   International Conference on Learning Representations (ICLR), 2023, Tiny Paper. [Paper]

8. Contrastive identity-aware learning for multi-agent value decomposition

   Shunyu Liu, Yihe Zhou, Jie Song, Tongya Zheng, Kaixuan Chen, Tongtian Zhu, Zunlei Feng, Mingli Song

   AAAI Conference on Artificial Intelligence (AAAI), Oral, 2023. [Paper] [Code]

2022

1. Distribution knowledge embedding for graph pooling

   Kaixuan Chen, Jie Song, Shunyu Liu, Na Yu, Zunlei Feng, Gengshi Han, Mingli Song

   IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022. [Paper] [Code]

2. Distribution-aware graph representation learning for transient stability assessment of power system

   Kaixuan Chen, Shunyu Liu, Na Yu, Rong Yan, Quan Zhang, Jie Song, Zunlei Feng, Mingli Song

   International Joint Conference on Neural Networks (IJCNN), 2022, Oral. [Paper] [Code]

2021

1. Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN

   Gengshi Han, Shunyu Liu, Kaixuan Chen, Na Yu, Zunlei Feng, Mingli Song

   International Conference on Intelligent Computing and Optimization (ICO), 2021, Oral. [Paper]

2020

1. Covariance Descriptors on a Gaussian Manifold and their Application to Image Set Classification

   Kai-Xuan Chen, Jie-Yi Ren, Xiao-Jun Wu, Josef Kittler

   Pattern Recognition (PR), 2020. [Paper] [Code]

2. Multiple Riemannian manifold-valued descriptors based image set classification with multi-kernel metric learning

   Rui Wang, Xiao-Jun Wu, Kai-Xuan Chen, Josef Kittler

   IEEE Transactions on Big Data (TBD), 2020. [Paper] [Code]

2019

1. More about covariance descriptors for image set coding: Log-euclidean framework based kernel matrix representation

   Kai-Xuan Chen, Xiao-Jun Wu, Jie-Yi Ren, Rui Wang, Josef Kittler

   International Conference on Computer Vision (ICCV) CEFRL Workshops, 2019. [Paper] [Code]

2018

1. Multiple manifolds metric learning with application to image set classification

   Rui Wang, Xiao-Jun Wu, Kai-Xuan Chen, Josef Kittler

   International Conference on Pattern Recognition (ICPR), 2018. [Paper] [Code]

2. Riemannian kernel based Nyström method for approximate infinite-dimensional covariance descriptors with application to image set classification

   Kai-Xuan Chen, Xiao-Jun Wu, Rui Wang, Josef Kittler

   International Conference on Pattern Recognition (ICPR), 2018. [Paper] [Code]

3. Component SPD matrices: A low-dimensional discriminative data descriptor for image set classification

   Kai-Xuan Chen, Xiao-Jun Wu

   Computational Visual Media (CVM), 2018. [Paper] [Code]