Shichang (Ray) Zhang

alt text 

About Me

I am Shichang (Ray) Zhang. I am a postdoctoral fellow at the D^3 Institute at Harvard University working with Professor Hima Lakkaraju. I received my Ph.D. in Computer Science from University of California, Los Angeles (UCLA), where I was very fortunate to have Professor Yizhou Sun as my advisor. My Ph.D. research was generously supported by the J.P. Morgan Chase AI Ph.D. Fellowship and the Amazon Fellowship. Before joining UCLA, I received my M.S. and B.A., both in Statistics, from Stanford and Berkeley respectively.

During my Ph.D. at UCLA, I organized the Data Mining Reading Group for two years. Slides and recordings of the reading groups can be found here. My presentations at the reading group can be found under Talks.

Contact

Science and Engineering Complex (SEC) 6.220, 150 Western Ave, Boston, MA 02134
E-mail: shzhang AT hbs DOT edu
[Google Scholar] [GitHub] [LinkedIn] [X] [CV]

What's New

  • [Oct 2024] Our paper on explainable graph learning for predicting ICU length of stay is accepted by ISR [PDF]

  • [Oct 2024] Our paper on generalized group data attribution is on arXiv now [PDF]

  • [July 2024] A Mind Map of Knowledge in LLMs

  • [June 2024] Our paper on controlling LLM behaviors with LLM itself as a judge is on arXiv now [PDF] [Code] [Website]

  • [May 2024] Defended my Ph.D. thesis “Explainable AI for Graph Data”

  • [May 2024] Our paper on efficient ensembling for training data attribution is on arXiv now [PDF]

  • [May 2024] Our paper on measure-theoretic compact fuzzy set representation for taxonomy expansion is accepted by ACL 2024 as Findings [PDF]

  • [May 2024] Two papers on GNNs for explainable material science and benchmarking LLMs on scientific problems are accepted by ICML 2024 [PDF1] [PDF2]

  • [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 [PDF]

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

Research Interests

My research interests include

  • Explainable AI

  • Mechanistic Interpretability

  • Data Attribution

  • Large Language Models

  • Graph Data Mining

  • Model Efficiency

Selected Publications and Pre-prints

  1. An Explainable AI Approach using Graph Learning to Predict ICU Length of Stay (ISR Oct. 2024)
    Tianjian Guo, Indranil Bardhan, Ying Ding, Shichang Zhang [PDF]

  2. Generalized Group Data Attribution (ATTRIB@NeurIPS 2024)
    Dan Ley, Suraj Srinivas, Shichang Zhang, Gili Rusak, Himabindu Lakkaraju [PDF]

  3. Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller (MI@ICML 2024)
    Min Cai, Yuchen Zhang, Shichang Zhang, Fan Yin, Difan Zou, Yisong Yue, Ziniu Hu [PDF] [Code] [Website]

  4. Efficient Ensembles Improve Training Data Attribution (DMLR@ICML 2024)
    Junwei Deng, Ting-Wei Li, Shichang Zhang, Jiaqi Ma [PDF]

  5. 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]

  6. 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]

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

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

Full list of publications

Honors and Awards