publications

2025

1. ICML’25

   Autogfm: Automated Graph Foundation Model with Adaptive Architecture Customization

   Haibo Chen, Xin Wang, Zeyang Zhang, Haoyang Li, Lin Feng, and Wenwu Zhu

   In ICML Oral, 2025

   Bib

   @inproceedings{chen2025autogfm,
     title = {Autogfm: Automated Graph Foundation Model with Adaptive Architecture Customization},
     author = {Chen, Haibo and Wang, Xin and Zhang, Zeyang and Li, Haoyang and Feng, Lin and Zhu, Wenwu},
     year = {2025},
     booktitle = {ICML Oral},
     topic = {llm},
   }

2. ICML’25

   Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum

   Haoyang Li, Xin Wang, Zeyang Zhang, Zongyuan Wu, Linxin Xiao, and Wenwu Zhu

   In ICML spotlight, 2025

   Bib

   @inproceedings{li2025ssl,
     title = {Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum},
     author = {Li, Haoyang and Wang, Xin and Zhang, Zeyang and Wu, Zongyuan and Xiao, Linxin and Zhu, Wenwu},
     year = {2025},
     booktitle = {ICML spotlight},
   }

3. ICML’25

   Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

   Chendi Ge, Xin Wang, Zeyang Zhang, Hong Chen, Jiapei Fan, Longtao Huang, Hui Xue, and Wenwu Zhu

   In ICML, 2025

   Bib

   @inproceedings{Ge2025dynamic,
     title = {Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning},
     author = {Ge, Chendi and Wang, Xin and Zhang, Zeyang and Chen, Hong and Fan, Jiapei and Huang, Longtao and Xue, Hui and Zhu, Wenwu},
     year = {2025},
     booktitle = {ICML},
   }

4. KDD’25

   Causal-Aware Graph Neural Architecture Search under Distribution Shifts

   Peiwen Li, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Jialong Wang, Yang Li, and Wenwu Zhu

   In ACM KDD, 2025

   Bib

   @inproceedings{li2024causalaware,
     title = {Causal-Aware Graph Neural Architecture Search under Distribution Shifts},
     author = {Li, Peiwen and Wang, Xin and Zhang, Zeyang and Qin, Yijian and Zhang, Ziwei and Wang, Jialong and Li, Yang and Zhu, Wenwu},
     year = {2025},
     booktitle = {ACM KDD},
   }

5. WWW’25

   Graph Machine Learning under Distribution Shifts: Adaptation, Generalization and Extension to LLM

   Xin Wang, Haoyang Li, Zeyang Zhang, and Wenwu Zhu

   In ACM WWW, 2025

   Abs Bib

   Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution (I.D.) hypothesis, i.e., testing and training graph data are sampled from the identical distribution. However, this I.D. hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, several advanced graph machine learning techniques which go beyond the I.D. hypothesis, have made great progress and attracted ever-increasing attention from the research community. This tutorial is to disseminate and promote the recent research achievement on graph out-of-distribution adaptation, graph out-of-distribution generalization, and large language models for tackling distribution shifts, which are exciting and fast-growing research directions in the general field of machine learning and data mining. We will advocate novel, high-quality research findings, as well as innovative solutions to the challenging problems in graph machine learning under distribution shifts and the applications on graphs. This topic is at the core of the scope of The Web Conference, and is attractive to machine learning as well as data mining audience from both academia and industry.

   @inproceedings{wang2025graph,
     author = {Wang, Xin and Li, Haoyang and Zhang, Zeyang and Zhu, Wenwu},
     title = {Graph Machine Learning under Distribution Shifts: Adaptation, Generalization and Extension to LLM},
     year = {2025},
     isbn = {9798400713316},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3701716.3715863},
     doi = {10.1145/3701716.3715863},
     booktitle = {ACM WWW},
     pages = {53–56},
     numpages = {4},
     keywords = {adaptation, distribution shift, generalization, graph machine learning, large language model},
     location = {Sydney NSW, Australia},
     series = {WWW '25},
   }

6. Arxiv

   Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models

   Xin Wang, Haoyang Li, Zeyang Zhang, Haibo Chen, and Wenwu Zhu

   2025

   Bib

   @misc{wang2025modularmachinelearningindispensable,
     title = {Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models},
     author = {Wang, Xin and Li, Haoyang and Zhang, Zeyang and Chen, Haibo and Zhu, Wenwu},
     year = {2025},
     eprint = {2504.20020},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2504.20020},
   }

7. Arxiv

   Towards Multi-modal Graph Large Language Model

   Xin Wang, Zeyang Zhang, Linxin Xiao, Haibo Chen, Chendi Ge, and Wenwu Zhu

   2025

   Bib

   @misc{wang2025multimodalgraphlargelanguage,
     title = {Towards Multi-modal Graph Large Language Model},
     author = {Wang, Xin and Zhang, Zeyang and Xiao, Linxin and Chen, Haibo and Ge, Chendi and Zhu, Wenwu},
     year = {2025},
     eprint = {2506.09738},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2506.09738},
   }

2024

1. TOIS’24

   Disentangled Dynamic Graph Attention Network for Out-of-distribution Sequential Recommendation

   Zeyang Zhang, Xin Wang, Haibo Chen, Haoyang Li, and Wenwu Zhu

   In ACM TOIS, 2024

   Bib

   @inproceedings{zhang2024disen,
     title = {Disentangled Dynamic Graph Attention Network for Out-of-distribution Sequential Recommendation},
     author = {Zhang, Zeyang and Wang, Xin and Chen, Haibo and Li, Haoyang and Zhu, Wenwu},
     booktitle = {ACM TOIS},
     year = {2024},
     topic = {ood},
   }

2. KDD’24

   

   LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?

   Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Yijian Qin, and Wenwu Zhu

   In ACM SIGKDD, 2024

   Bib

   @inproceedings{zhang2023LLM4DyG,
     title = {LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?},
     author = {Zhang, Zeyang and Wang, Xin and Zhang, Ziwei and Li, Haoyang and Qin, Yijian and Zhu, Wenwu},
     booktitle = {ACM SIGKDD},
     year = {2024},
     topic = {llm},
   }

3. ICML’24

   

   Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet

   Zeyang Zhang, Xin Wang, Yijian Qin, Hong Chen, Xu Chu, Ziwei Zhang, and Wenwu Zhu

   In ICML, 2024

   Bib

   @inproceedings{gasim,
     title = {Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet},
     author = {Zhang, Zeyang and Wang, Xin and Qin, Yijian and Chen, Hong and Chu, Xu and Zhang, Ziwei and Zhu, Wenwu},
     booktitle = {ICML},
     topic = {auto},
     year = {2024},
   }

4. ICML’24

   Disentangled Graph Self-supervised Learning for Out-of-distribution Generalization

   Haoyang Li, Xin Wang, Zeyang Zhang, Haibo Chen Ziwei Zhang, and Wenwu Zhu

   In ICML, 2024

   Bib

   @inproceedings{li2024dis,
     title = {Disentangled Graph Self-supervised Learning for Out-of-distribution Generalization},
     author = {Li, Haoyang and Wang, Xin and Zhang, Zeyang and Zhang, Haibo Chen Ziwei and Zhu, Wenwu},
     booktitle = {ICML},
     year = {2024}
   }

5. KDD’24

   Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification

   Beini Xie, Heng Chang, Ziwei Zhang, Zeyang Zhang, Simin Wu, Xin Wang, Yuan Meng, and Wenwu Zhu

   In ACM SIGKDD, 2024

   Bib

   @inproceedings{xie2024towards,
     title = {Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification},
     author = {Xie, Beini and Chang, Heng and Zhang, Ziwei and Zhang, Zeyang and Wu, Simin and Wang, Xin and Meng, Yuan and Zhu, Wenwu},
     booktitle = {ACM SIGKDD},
     year = {2024},
   }

6. NeurIPS’24

   VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding

   Houlun Chen, Xin Wang, Hong Chen, Zeyang Zhang, Wei Feng, Bin Huang, Jia Jia, and Wenwu Zhu

   NeurIPS, 2024

   Bib

   @article{chen2024verified,
     title = {VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding},
     author = {Chen, Houlun and Wang, Xin and Chen, Hong and Zhang, Zeyang and Feng, Wei and Huang, Bin and Jia, Jia and Zhu, Wenwu},
     journal = {NeurIPS},
     year = {2024},
   }

7. IJCAI’24t

   Graph Machine Learning under Distribution Shifts: Adaptation, Generalization and Extension to LLMs

   Xin Wang, Haoyang Li, Zeyang Zhang, and Wenwu Zhu

   IJCAI tutorial, 2024

   Bib

   @article{xin2024graph,
     title = {Graph Machine Learning under Distribution Shifts: Adaptation, Generalization and Extension to LLMs},
     author = {Wang, Xin and Li, Haoyang and Zhang, Zeyang and Zhu, Wenwu},
     journal = {IJCAI tutorial},
     year = {2024},
   }

8. Arxiv

   LLM-Enhanced Causal Discovery in Temporal Domain from Interventional Data

   Peiwen Li, Xin Wang, Zeyang Zhang, Yuan Meng, Fang Shen, Yue Li, Jialong Wang, Yang Li, and Wenweu Zhu

   2024

   Bib

   @misc{li2024llmenhanced,
     title = {LLM-Enhanced Causal Discovery in Temporal Domain from Interventional Data},
     author = {Li, Peiwen and Wang, Xin and Zhang, Zeyang and Meng, Yuan and Shen, Fang and Li, Yue and Wang, Jialong and Li, Yang and Zhu, Wenweu},
     year = {2024},
     eprint = {2404.14786},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

9. BioRxiv

   

   Decoding cell identity with multi-scale explainable deep learning

   Jun Zhu*, Zeyang Zhang*, Yujia Xiang, Beini Xie, Xinwen Dong, Linhai Xie, Peijie Zhou, Rongyan Yao, Xiaowen Wang, Yang Li, Fuchu He, Wenwu Zhu, Ziwei Zhang, and Cheng Chang

   bioRxiv, 2024

   Abs Bib HTML

   Cells are the fundamental structural and functional units of life. Studying the definition and composition of different cell types can help us understand the complex mechanisms underlying biological diversity and functionality. The increasing volume of extensive single-cell omics data makes it possible to provide detailed characterisations of cell types. Recently, there has been a rise in deep learning-based approaches that generate cell type labels solely through mapping query data to reference data. However, these approaches lack multi-scale descriptions and interpretations of identified cell types. Here, we propose Cell Decoder, a biological prior knowledge informed model to achieve multi-scale representation of cells. We implemented automated machine learning and post-hoc analysis techniques to decode cell identity. We have shown that Cell Decoder compares favourably to existing methods, offering multi-view interpretability for decoding cell identity and data integration. Furthermore, we have showcased its applicability in uncovering novel cell types and states in both human bone and mouse embryonic contexts, thereby revealing the multi-scale heterogeneity inherent in cell identities.Competing Interest StatementThe authors have declared no competing interest.

   @article{Zhu2024.02.05.578922,
     author = {Zhu*, Jun and Zhang*, Zeyang and Xiang, Yujia and Xie, Beini and Dong, Xinwen and Xie, Linhai and Zhou, Peijie and Yao, Rongyan and Wang, Xiaowen and Li, Yang and He, Fuchu and Zhu, Wenwu and Zhang, Ziwei and Chang, Cheng},
     title = {Decoding cell identity with multi-scale explainable deep learning},
     elocation-id = {2024.02.05.578922},
     year = {2024},
     doi = {10.1101/2024.02.05.578922},
     publisher = {Cold Spring Harbor Laboratory},
     eprint = {https://www.biorxiv.org/content/early/2024/02/08/2024.02.05.578922.full.pdf},
     journal = {bioRxiv},
     topic = {ai4science},
   }

10. Arxiv

    

    Exploring the Potential of Large Language Models in Graph Generation

    Yang Yao, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Xu Chu, Yuekui Yang, Wenwu Zhu, and Hong Mei

    arXiv preprint arXiv:2403.14358, 2024

    Bib

    @article{yao2024exploring,
      title = {Exploring the Potential of Large Language Models in Graph Generation},
      author = {Yao, Yang and Wang, Xin and Zhang, Zeyang and Qin, Yijian and Zhang, Ziwei and Chu, Xu and Yang, Yuekui and Zhu, Wenwu and Mei, Hong},
      journal = {arXiv preprint arXiv:2403.14358},
      year = {2024},
    }

2023

1. NeurIPS’23w

   

   Graph Meets LLMs: Towards Large Graph Models

   Ziwei Zhang, Haoyang Li, Zeyang Zhang, Yijian Qin, Xin Wang, and Wenwu Zhu

   In Conference on Neural Information Processing Systems Workshop, 2023

   arXiv Bib

   @inproceedings{zhang2023large,
     title = {Graph Meets LLMs: Towards Large Graph Models},
     author = {Zhang, Ziwei and Li, Haoyang and Zhang, Zeyang and Qin, Yijian and Wang, Xin and Zhu, Wenwu},
     booktitle = {Conference on Neural Information Processing Systems Workshop},
     year = {2023},
     topic = {llm},
   }

2. Arxiv

   

   LLM4VG: Large Language Models Evaluation for Video Grounding

   Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Zihan Song, Yuwei Zhou, and Wenwu Zhu

   arXiv preprint arXiv:2312.14206, 2023

   arXiv Bib

   @article{feng2023llm4vg,
     title = {LLM4VG: Large Language Models Evaluation for Video Grounding},
     author = {Feng, Wei and Wang, Xin and Chen, Hong and Zhang, Zeyang and Song, Zihan and Zhou, Yuwei and Zhu, Wenwu},
     journal = {arXiv preprint arXiv:2312.14206},
     year = {2023},
   }

3. Arxiv

   

   Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion

   Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, and Wenwu Zhu

   arXiv preprint arXiv:2311.14255, 2023

   arXiv Bib

   @article{zhang2023outofdistribution,
     title = {Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion},
     author = {Zhang, Zeyang and Wang, Xin and Zhang, Ziwei and Li, Haoyang and Zhu, Wenwu},
     year = {2023},
     journal = {arXiv preprint arXiv:2311.14255},
   }

4. MedAI’23

   

   Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Prediction

   Zeyang Zhang*, Xingwang Li*, Fei Teng, Ning Lin, Xueling Zhu, Xin Wang, and Wenwu Zhu

   In IEEE International Conference on Medical Artificial Intelligence, 2023

   Bib HTML

   @inproceedings{zhang2023ood,
     title = {Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Prediction},
     author = {Zhang*, Zeyang and Li*, Xingwang and Teng, Fei and Lin, Ning and Zhu, Xueling and Wang, Xin and Zhu, Wenwu},
     booktitle = {IEEE International Conference on Medical Artificial Intelligence},
     year = {2023},
     topic = {ai4science},
   }

5. NeurIPS’23

   

   Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision

   Zeyang Zhang, Xin Wang, Ziwei Zhang, Guangyao Shen, Shiqi Shen, and Wenwu Zhu

   In Advances in Neural Information Processing Systems, 2023

   Bib HTML

   @inproceedings{zhang2023unsupervised,
     title = {Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision},
     author = {Zhang, Zeyang and Wang, Xin and Zhang, Ziwei and Shen, Guangyao and Shen, Shiqi and Zhu, Wenwu},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2023},
     topic = {auto},
   }

6. NeurIPS’23

   

   Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

   Zeyang Zhang, Xin Wang, Ziwei Zhang, Zhou Qin, Weigao Wen, Hui Xue, Haoyang Li, and Wenwu Zhu

   In Advances in Neural Information Processing Systems, 2023

   Bib HTML

   @inproceedings{zhang2023spectral,
     title = {Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts},
     author = {Zhang, Zeyang and Wang, Xin and Zhang, Ziwei and Qin, Zhou and Wen, Weigao and Xue, Hui and Li, Haoyang and Zhu, Wenwu},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2023},
     topic = {ood},
   }

7. AAAI’23

   

   Dynamic Heterogeneous Graph Attention Neural Architecture Search

   Zeyang Zhang, Ziwei Zhang, Xin Wang, Yijian Qin, Zhou Qin, and Wenwu Zhu

   In Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

   Bib HTML

   @inproceedings{zhang2023dynamic,
     title = {Dynamic Heterogeneous Graph Attention Neural Architecture Search},
     author = {Zhang, Zeyang and Zhang, Ziwei and Wang, Xin and Qin, Yijian and Qin, Zhou and Zhu, Wenwu},
     booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence},
     year = {2023},
     topic = {auto},
   }

2022

1. NeurIPS’22

   

   Dynamic graph neural networks under spatio-temporal distribution shift

   Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Zhou Qin, and Wenwu Zhu

   In Advances in Neural Information Processing Systems, 2022

   Bib HTML

   @inproceedings{zhang2022dynamic,
     title = {Dynamic graph neural networks under spatio-temporal distribution shift},
     author = {Zhang, Zeyang and Wang, Xin and Zhang, Ziwei and Li, Haoyang and Qin, Zhou and Zhu, Wenwu},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2022},
     topic = {ood},
   }

2. AAAI’22

   

   Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum

   Zeyang Zhang, Ziwei Zhang, Xin Wang, and Wenwu Zhu

   Thirty-Fifth AAAI Conference on Artificial Intelligence, 2022

   Bib HTML

   @article{zhang2022learning,
     title = {Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum},
     author = {Zhang, Zeyang and Zhang, Ziwei and Wang, Xin and Zhu, Wenwu},
     journal = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence},
     year = {2022},
     topic = {ai4science},
   }

3. NeurIPS’22

   

   NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search

   Yijian Qin, Ziwei Zhang, Xin Wang, Zeyang Zhang, and Wenwu Zhu

   In Thirty-Sixth Conference on Neural Information Processing Systems, 2022

   Bib HTML

   @inproceedings{qin2022bench,
     title = {NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search},
     author = {Qin, Yijian and Zhang, Ziwei and Wang, Xin and Zhang, Zeyang and Zhu, Wenwu},
     booktitle = {Thirty-Sixth Conference on Neural Information Processing Systems},
     year = {2022},
   }

2021

1. CVPR’21w

   One-Shot Neural Channel Search: What Works and What’s Next

   Chaoyu Guan, Yijian Qin, Zhikun Wei, Zeyang Zhang, Zizhao Zhang, Xin Wang, and Wenwu Zhu

   In CVPR 2021 workshop, 2021

   Bib

   @inproceedings{guan2021one,
     title = {One-Shot Neural Channel Search: What Works and What's Next},
     author = {Guan, Chaoyu and Qin, Yijian and Wei, Zhikun and Zhang, Zeyang and Zhang, Zizhao and Wang, Xin and Zhu, Wenwu},
     booktitle = {CVPR 2021 workshop},
     year = {2021},
   }

2. ICLR’21w

   AutoGL: A Library for Automated Graph Learning

   Chaoyu Guan, Ziwei Zhang, Haoyang Li, Heng Chang, Zeyang Zhang, Yijian Qin, Jiyan Jiang, Xin Wang, and Wenwu Zhu

   In ICLR 2021 Workshop GTRL, 2021

   Bib

   @inproceedings{guan2021autogl,
     title = {AutoGL: A Library for Automated Graph Learning},
     author = {Guan, Chaoyu and Zhang, Ziwei and Li, Haoyang and Chang, Heng and Zhang, Zeyang and Qin, Yijian and Jiang, Jiyan and Wang, Xin and Zhu, Wenwu},
     booktitle = {ICLR 2021 Workshop GTRL},
     year = {2021},
   }

3. NeurIPS’21

   Graph differentiable architecture search with structure learning

   Yijian Qin, Xin Wang, Zeyang Zhang, and Wenwu Zhu

   In Thirty-Fifth Conference on Neural Information Processing Systems, 2021

   Bib HTML

   @inproceedings{qin2021graph,
     title = {Graph differentiable architecture search with structure learning},
     author = {Qin, Yijian and Wang, Xin and Zhang, Zeyang and Zhu, Wenwu},
     booktitle = {Thirty-Fifth Conference on Neural Information Processing Systems},
     year = {2021},
   }

4. Arxiv

   Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?

   Ziwei Zhang, Xin Wang, Zeyang Zhang, Peng Cui, and Wenwu Zhu

   arXiv preprint arXiv:2112.12345, 2021

   arXiv Bib

   @article{zhang2021revisiting,
     title = {Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?},
     author = {Zhang, Ziwei and Wang, Xin and Zhang, Zeyang and Cui, Peng and Zhu, Wenwu},
     journal = {arXiv preprint arXiv:2112.12345},
     year = {2021},
   }