Jiale is currently a Ph.D. candidate in the Department of Computer Science, Shanghai Jiao Tong University, supervised by Prof. Yanyan Shen. He is also an intern at ByteDance, advised by Dr. Xiaogang Shi. Previously, he received his B.S. from the College of Computer Science, Sichuan University.

His previous work mainly focuses on explaining graph neural networks, and he is currently working on data selection and data debugging for machine learning models, especially for large language models.

Research Interests

Data Selection; Data Debugging; Retrieval-Augmented Generation; Trustworthy AI

He has organized his recent reading paper list in awesome-ml-data-quality-papers.

Recent Publications

• [KDD 2026] Deng, J., Shen, Y., Shi, X., & Junjun, C. (2026). DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors. paper, code

• [NeurIPS 2025] Deng, J., Shen, Y., Pei, Z., Chen, Y., & Huang, L. Influence Guided Context Selection for Effective Retrieval-Augmented Generation. paper, code

• [AAAI 2024] Deng, J., & Shen, Y. Self-interpretable graph learning with sufficient and necessary explanations. paper, code

• [AAAI 2023] Li, T., Deng, J., Shen, Y., Qiu, L., Yongxiang, H., & Cao, C. C. Towards fine-grained explainability for heterogeneous graph neural network. paper, code