Menu
Home
Research
Teaching
Talks
Miscellaneous

Shichang Zhang

alt text 

About Me

I am a fifth-year Ph.D. student in Computer Science at University of California, Los Angeles (UCLA) Data Mining Lab working with Professor Yizhou Sun. My research is generously supported by the J.P. Morgan Chase AI Ph.D. Fellowship and the Amazon Fellowship. Before joining UCLA, I received my B.A. and M.S. both in Statistics from Berkeley and Stanford respectively.

I organize the UCLA Data Mining Reading Group. The reading group includes cutting-edge research papers, AI courses, and guest talks. Our AI course for this quarter is Neurosymbolic methods. In the past, we have covered physics-informed machine learning, diffusion models, large language models, differential geometry, probabilistic graphical models, spectral graph theory, and neural radiance fields. Please find past slides and recordings here. My presentations at the reading group can be found under Talks.

Please feel free to email me if you are interested in becoming a guest speaker. We especially welcome senior-year PhDs to practice their job talks and the first authors to present their recent work published in top conferences.

Contact

3551 (ScAI Lab), Bolter Hall, UCLA, CA, 90095
E-mail: shichang AT cs DOT ucla DOT edu
[Google Scholar] [GitHub] [Twitter] [LinkedIn][CV]

What's New

  • [May 2024] Two papers on GNNs for explainable material science and benchmarking LLMs on scientific problems are accepted by ICML 2024 [Paper1] [Paper2]

  • [Feb 2024] Give a talk on Explainable AI for Graph Data and More at the AI4LIFE Group at Harvard.

  • [Dec 2023] Our paper on LLM-based explainable molecular concept learning is accepted by the XAI4Sci workshop at AAAI 2024

  • [Dec 2023] Our paper on GNNs for explainable material science is accepted by the AI4Mat workshop at NeurIPS 2023 [PDF]

  • [Aug 2023] Certified Excellence in Reviewing for KDD 2023 (30 in 1551)

  • [July 2023] I am excited to be selected as one of the 2023 Amazon Fellows

  • [July 2023] I am excited to receive the J.P. Morgan Chase AI Ph.D. Fellowship

  • [July 2023] Give a talk on the PaGE-Link paper at Amazon Trans.AI Research Talk Series [slides]

  • [June 2023] Our survey paper on GNN acceleration is on arXiv now, which covers algorithms, systems, and customized hardware [PDF]
    Find out older news

Research Interests

My research interests include

  • Explainable AI

  • Large Language Models

  • Graph Data Mining

  • Model Efficiency

  • Self-supervised Learning

Recent Publications and Pre-prints

  1. Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks (ICML 2024)
    Haoyu Li*, Shichang Zhang*, Longwen Tang, Mathieu Bauchy, Yizhou Sun (*equal contribution) [PDF]

  2. SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models (ICML 2024)
    Xiaoxuan Wang*, Ziniu Hu*, Pan Lu*, Yanqiao Zhu*, Jieyu Zhang, Satyen Subramaniam, Arjun R Loomba, Shichang Zhang, Yizhou Sun, Wei Wang (*equal contribution) [PDF] [code]

  3. Explainable Molecular Concept Learning with Large Language Models (XAI4Sci@AAAI 2024)
    Qianli Wu*, Shichang Zhang*, Botao Xia, Zimin Zhang, Fang Sun, Ziniu Hu, Yizhou Sun (*equal contribution)

  4. Laplacian Score Benefit Adaptive Filter Selection for Graph Neural Networks (SDM 2024)
    Yewen Wang, Shichang Zhang, Junghoo Cho, Yizhou Sun [PDF]

  5. A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware (pre-print)
    Shichang Zhang, Atefeh Sohrabizadeh, Cheng Wan, Zijie Huang, Ziniu Hu, Yewen Wang, Yingyan (Celine) Lin, Jason Cong, Yizhou Sun [PDF]

  6. Linkless Link Prediction via Relational Distillation (ICML 2023)
    Zhichun Guo, William Shiao, Shichang Zhang, Yozen Liu, Nitesh Chawla, Neil Shah, Tong Zhao [PDF] [code]

  7. PaGE-Link: Graph Neural Network Explanation for Heterogeneous Link Prediction (WWW 2023)
    Shichang Zhang, Jiani Zhang, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos, Yizhou Sun. [PDF][code]

  8. GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games (NeurIPS 2022)
    Shichang Zhang, Neil Shah, Yozen Liu, Yizhou Sun [PDF] [code]

  9. Graph-less Neural Networks, Teach Old MLPs New Tricks via Distillation (ICLR 2022)
    Shichang Zhang, Yozen Liu, Yizhou Sun, Neil Shah [PDF] [code]

  10. Graph Condensation for Graph Neural Networks (ICLR 2022)
    Wei Jin, Lingxiao Zhao, Shichang Zhang, Yozen Liu, Jiliang Tang, Neil Shah [PDF] [code]

Full list of publications

Honors and Awards