Jun Xia

Ph.D. Student
School of Engineering
Westlake University & Zhejiang University
Email: xiajun@westlake.edu.cn
Advisor: Stan Z. Li (IEEE Fellow)

Profile

Hi there! I am Jun Xia, a Ph.D. student at Westlake University and Zhejiang University, advised by Chair Prof. Stan Z. Li. Before Joining Westlake, I received my B.E. degree with honors from Central South University. My primary research interests lie in the intersection of Machine Learning and Computational Biochemistry.

🌟 Hiring: We are actively seeking funded visiting students, research assistant and self-motivated Ph.D. students. Since July 2022, almost every visiting student who worked with me has published papers at top conferences such as ICML, NeurIPS, and ICLR during their visit. If you are interested, please don't hesitate to contact me via Email.

News

(2024.04) Two papers on drug discovery are accepted in IJCAI 2024.
(2024.01) One paper on protein design is accepted in ICLR 2024.
(2023.12) Selected for the Rising Stars in AI 2024 organized by KAUST AI Initiative.
(2023.12) One paper on antibody design is accepted in AAAI 2024
(2023.12) One paper on graph pre-training is accepted in ICDE 2024
(2023.10) Invited to diliver a talk on AIDD @ Fudan University.
(2023.10) I am awarded NeurIPS Scholar Award & Suwu Scholarship.
(2023.09) One paper on molecular property prediction is accepted in NeurIPS 2023.
(2023.09) Invited to review for ICLR 2024, ACM TKDD, SDM 2024 and IEEE TIP.
(2023.08) Two papers on graph clustering are accepted at ACM MM 2023.
(2023.06) One paper on label-noise learning on graph data is accepted in TKDE 2023.
(2023.06) One paper on Chemical Pre-trained Models is accepted in ECML 2023.
(2023.04) Invited to diliver a talk @ Canada MILA Lab (Led by Turing Awardee Yoshua Bengio).
(2023.04) One paper on graph clustering is accepted in ICML 2023.
(2023.04) Our survey on Chemical Language Models has been accepted in IJCAI 2023 survey track.
(2023.02) Our SimGRACE (WWW 2022) paper is featured as Most Influential WWW Papers by Paper Digest.
(2023.02) Two papers (One oral presentation) are accepted in CVPR 2023.
(2023.01) I am a winner of Westlake Presidential Awards, the highest honor for Westlake students.
(2023.01) One paper on molecular pre-trained models is accepted in ICLR 2023.
(2022.10) I am awarded National Scholarship.
(2022.05) One paper on graph contrastive learning is accepted in ICML 2022.
(2022.01) One paper on word embeddings is accepted in ACL 2022.
(2022.01) One paper on graph pre-training is accepted in WWW 2022.

Invited Talks

2024/02: Talk on "Discipher Biochemical Codes with Pre-learned Potentials" @ KAUST AI Rising Stars Symposium, Saudi Arabia.
2023/10: Talk on "Accelerating Drug Discovery with Pre-learned Potential" @ Fudan University. [slides]
2023/05: Talk on "Chemical Pre-trained Models: Retrospect & Prospect" @ Chinese Genomics Meet-up online [Vedio].
2023/03: Talk on "Accelerating Drug Discovery with Pre-learned Potential" @ Alibaba Group.
2022/11: Talk on graph contrastive learning @ Aminer seminer (Online) [Vedio].
2022/03: Talk on hard negative mining in GCL @ LoGs seminer (Online)[Vedio].
2022/08: Talk on pre-training GNNs @ Chungbuk National University, South Korea (Online)[Slides (Stay tuned)].
2022/06: Talk on hard negative mining @ Prof. Yue Zhang's group in Westlake University.
2022/05: Talk on graph contrastive learning @ Hangzhou Normal University (Online).

Selected Publications

Discover the full list |

.
[AI-driven Drug Discovery (AIDD)]

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions
Jun Xia, Lecheng Zhang, Xiao Zhu, Stan Z.Li.
NeurIPS 2023; ICML 2023 Computational Biology Workshop (Spotlight Talk)
[PDF] [Bib] [Code]

@inproceedings{
xia2023understanding,
title={Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions},
author={Jun Xia and Lecheng Zhang and Xiao Zhu and Yue Liu and Zhangyang Gao and Bozhen Hu and Cheng Tan and Jiangbin Zheng and Siyuan Li and Stan Z. Li},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023}
}

Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules
Jun Xia, Chengshuai Zhao, Bozhen Hu, Zhangyang Gao, Cheng Tan, Yue Liu, Siyuan Li, Stan Z.Li.
ICLR 2023
[PDF] [Bib] [Code]

                @inproceedings{Xia2023MoleBERTRP,
                    title={Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules},
                    author={Jun Xia and Chengshuai Zhao and Bozhen Hu and Zhangyang Gao and Cheng Tan and Yue Liu and Siyuan Li and Stan Z. Li},
                    booktitle={International Conference on Learning Representations},
                    year={2023},
                    url={https://api.semanticscholar.org/CorpusID:259298531}
                  }

A Systematic Survey of Chemical Pre-trained Models
Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z.Li.
IJCAI 2023 Survey Track
[PDF] [Bib] [Code]

@inproceedings{Xia2022ASS,
    title={A Systematic Survey of Chemical Pre-trained Models},
    author={Jun Xia and Yanqiao Zhu and Yuanqi Du and Stan Z.Li},
    booktitle={International Joint Conference on Artificial Intelligence},
    year={2022},
    url={https://api.semanticscholar.org/CorpusID:258352439}
    }

Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
Cheng Tan, Zhangyang Gao, Lirong Wu, Jun Xia, Jiangbin Zheng, Xihong Yang, Yue Liu, Bozhen Hu, Stan Z.Li.
AAAI 2024
[PDF] [Bib] [Code]

@inproceedings{
    gao2023cosp,
    title={CoSP: Co-supervised pretraining of pocket and ligand},
    author={Zhangyang Gao and Cheng Tan and Jun Xia and Stan Z. Li},
    booktitle={ECML-PKDD},
    year={2023}
    }

KW-Design: Pushing the Limit of Protein Deign via Knowledge Refinement
Zhangyang Gao, Cheng Tan, Xingran Chen, Yijie Zhang, Jun Xia, Siyuan Li, Stan Z.Li.
ICLR 2024
[PDF] [Bib] [Code]

@inproceedings{
anonymous2024kwdesign,
title={{KW}-Design: Pushing the Limit of Protein Deign via Knowledge Refinement},
author={Anonymous},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=mpqMVWgqjn}
}

CoSP: Co-supervised pretraining of pocket and ligand
Zhangyang Gao, Cheng Tan, Jun Xia, Stan Z.Li.
ECML 2023
[PDF] [Bib] [Code]

@inproceedings{
    gao2023cosp,
    title={CoSP: Co-supervised pretraining of pocket and ligand},
    author={Zhangyang Gao and Cheng Tan and Jun Xia and Stan Z. Li},
    booktitle={ECML-PKDD},
    year={2023}
    }

[Graph Machine Learning]

SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
Jun Xia, Lirong Wu, Jintao Chen, Bozhen Hu, Stan Z.Li.
WWW 2022, Most Influential WWW Papers according to Paper Digest
[PDF] [Bib] [Code]

@article{Xia2022SimGRACEAS,
    title={SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation},
    author={Jun Xia and Lirong Wu and Jintao Chen and Bozhen Hu and Stan Z. Li},
    journal={Proceedings of the ACM Web Conference 2022},
    year={2022},
    url={https://api.semanticscholar.org/CorpusID:246634345}
    }

ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Jun Xia, Lirong Wu, Ge Wang, Jintao Chen, Stan Z.Li.
ICML 2022, Spotlight
[PDF] [Bib] [Code]

@inproceedings{Xia2021ProGCLRH,
    title={ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning},
    author={Jun Xia and Lirong Wu and Ge Wang and Jintao Chen and Stan Z. Li},
    booktitle={International Conference on Machine Learning},
    year={2021},
    url={https://api.semanticscholar.org/CorpusID:249282506}
    }

GNN Cleaner: Label Cleaner for Graph-structured Data
Jun Xia, Haitao Lin, Yongjie Xu, Cheng Tan, Lirong Wu, Bozhen Hu, Siyuan Li, Stan Z.Li.
TKDE 2023
[PDF] [Bib] [Code]

@article{xia2023gnn,
    title={GNN Cleaner: Label Cleaner for Graph Structured Data},
    author={Xia, Jun and Lin, Haitao and Xu, Yongjie and Tan, Cheng and Wu, Lirong and Li, Siyuan and Li, Stan Z},
    journal={IEEE Transactions on Knowledge and Data Engineering},
    year={2023},
    publisher={IEEE}
    }

DiscoGNN: A Sample-Efficient Framework for Graph Self-supervised Representation Learning
Jun Xia, Shaorong Chen, Yue Liu, Zhangyang Gao, Jiangbing Zheng, Xihong Yang, Stan Z.Li.
ICDE 2024
[PDF] [Bib] [Code]

@article{xia2023gnn,
    title={DiscoGNN: A Sample-Efficient Framework for Graph Self-supervised Representation Learning},
    author={Xia, Jun and Chen, Shaorong and Liu, Yue and Gao, Zhangyang and Zheng, Jiangbing and Yang, Xihong and Li, Stan Z},
    journal={International Conference on Data Engineering (ICDE)},
    year={2024},
    publisher={IEEE}
    }

Dink-Net: Neural Clustering on Large Graphs
Yue Liu, Ke Liang, Jun Xia, Sihang Zhou, Xihong Yang, Xingwang Liu, Stan Z.Li.
ICML 2023
[PDF] [Bib] [Code]

@inproceedings{Liu2023DinkNetNC,
title={Dink-Net: Neural Clustering on Large Graphs},
author={Yue Liu and Kenny Ye Liang and Jun Xia and Sihang Zhou and Xihong Yang and Xinwang Liu and Stan Z. Li},
booktitle={International Conference on Machine Learning},
year={2023},
url={https://api.semanticscholar.org/CorpusID:258967414}
}

GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction
Lirong Wu, Jun Xia, Haitao Lin, Zhangyang Gao, Cheng Tan, Stan Z.Li.
ECML 2023
[PDF] [Bib] [Code]

@inproceedings{Wu2022GraphMixupIC,
    title={GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction},
    author={Lirong Wu and Jun Xia and Zhangyang Gao and Haitao Lin and Cheng Tan and Stan Z. Li},
    booktitle={ECML/PKDD},
    year={2022},
    url={https://api.semanticscholar.org/CorpusID:252507534}
    }

[Others]

Co-learning: Learning from Noisy Labels with Self-supervision
Cheng Tan, Jun Xia, Lirong Wu, Stan Z.Li.
ACM MM 2021, Oral Presentation
[PDF] [Bib] [Code]

                @article{Tan2021ColearningLF,
                    title={Co-learning: Learning from Noisy Labels with Self-supervision},
                    author={Cheng Tan and Jun Xia and Lirong Wu and Stan Z. Li},
                    journal={Proceedings of the 29th ACM International Conference on Multimedia},
                    year={2021},
                    url={https://api.semanticscholar.org/CorpusID:236956719}
                  }

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment
Jiangbin Zheng, Yile Wang, Cheng Tan, Siyuan Li, Ge Wang, Jun Xia, Siyuan Li, Stan Z.Li.
CVPR 2023, Highlight (Oral) Presentation
[PDF] [Bib] [Code]

                @article{Zheng2023CVTSLRCV,
                    title={CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment},
                    author={Jiangbin Zheng and Yile Wang and Cheng Tan and Siyuan Li and Ge Wang and Jun Xia and Yidong Chen and Stan Z. Li},
                    journal={2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
                    year={2023},
                    pages={23141-23150},
                    url={https://api.semanticscholar.org/CorpusID:257482618}
                  }

Awards & Honors

2024: DAAD AINet Fellow.
2023: Rising Star in AI (awarded by KAUST AI Initiative headed by Prof. Jürgen Schmidhuber)
2023: NeurIPS Scholar Award.
2023: Suwu Scholarship.
2023: Westlake Presidential Awards (The highest honor at Westlake Univ.).
2022: National Scholarship.
2022: ICML 2022 Participation Grant.
2021: Outstanding Student Cadre, Zhejiang University.
2021: Outstanding Student, Zhejiang University.
2020: Outstanding Graduate of Central South University.
2019: The Interdisciplinary Contest in Modeling (ICM) of America, Meritorious Winner (The First Prize).
2018: World Robot Competition in World Robot Conference (WRC) 2018, The Third Prize.
2017: National Scholarship.
2017, 2018 & 2019: The First Class Scholarship, Central South University.
2017, 2018 & 2019: Outstanding Student, Central South University.

Academic Service

Program Committee Member:
- Conferences: ICLR, ICML, NeurIPS, CVPR, KDD, ACL, SDM, ECML, ICASSP, etc.
Journal Reviewer: IEEE TIP, ACM TKDD, IEEE TNNLS, Neural Networks, etc.

Co-working Students

(* I am working with some visiting/undergraduate students at Westlake with Chair Prof. Stan Z. Li)

Yue Liu (MS Student at NUDT)
Xinlong Yang (MS Student at PKU)
Hongcheng Gao (MS Student at ICT@Chinese Academy of Sciences)
Chengshuai Zhao (Undergraduate Student at UC Irvine → Ph.D. Student at ASU, advised by Huan Liu)
Xiaojun Shan (Undergraduate Student at UESTC)
Xiao Zhu (Undergraduate Student at BUPT)
Lecheng Zhang (Undergraduate Student at Westlake)