簡翌 I (Eli) Chien
國立臺灣大學電機工程學系 助理教授
Assistant Professor, Department of Electrical Engineering, National Taiwan University
主要研究領域:
人工智慧、機器學習、可規範性人工智慧、機器學習隱私、機器遺忘、人工智慧智慧財產權、圖機器學習Major Research Areas:
AI, Machine Learning, Regulatable AI, ML Privacy, Machine Unlearning, AI Copyright, Graph Machine Learning研究領域摘要:
Research Summary:
My research interests lie in the field of Regulatable AI, in particular, privacy and graph-related machine learning. I currently focus on machine unlearning, differential privacy, AI copyright infringement, and their application to graph ML. My other works include geometric learning, including general (hyper)graph neural networks, active learning on (hyper)graphs, and classification in hyperbolic/product spaces.
-
B.S.
EE, National Taiwan University, 2016 -
Ph.D.
ECE, University of Illinois Urbana Champaign, 2022 - Postdoc @ Georgia Institute of Technology, Visiting Researcher @ Google.
-
Address
EE2-,
Department of Electrical Engineering,
National Taiwan University,
Taipei 106, Taiwan -
Email:
-
Personal Homepage
https://sites.google.com/view/eli-chien/home
代表性著作 Selected Publication
- Eli Chien, Haoyu Wang, Ziang Chen, Pan Li, “Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning,” Neural Information Processing Systems, 2024
- Eli Chien, Chao Pan, Olgica Milenkovic, “Efficient Model Updates for Approximate Unlearning of Graph-Structured Data,” International Conference on Learning Representation, 2023
- Eli Chien, Jianhao Peng, Chao Pan, Olgica Milenkovic, “You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks,” International Conference on Learning Representations, 2022
- Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic, Inderjit S Dhillon, “Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction,” International Conference on Learning Representations, 2022
- Eli Chien, Jianhao Peng, Pan Li, Olgica Milenkovic, “Adaptive Universal Generalized PageRank Graph Neural Network,” International Conference on Learning Representations, 2021