2024/09: Our paper "On the Inherent Privacy Properties of Discrete Denoising Diffusion Models" is accepted by TMLR. Congrats to Rongzhe for leading the project!
2024/09: I will give an invited talk about machine unlearning at TAMU hosted by Kuan-Hao Huang in October.
2024/07: I will present our work "Langevin Unlearning" at TPDP 2024 in August!
2024/07: Our survey paper "Exploring the Opportunities and Challenges of Graph Neural Networks in Electrical Engineering" was accepted by Nature Reviews Electrical Engineering. Big congrats to the whole team!
2024/07: I'm excited to share the news that Prof. Pan Li and I will organize two mini-symposiums at MDS 2024, which will be held in Atlanta around October 21 – 25 this year! Please check out the detailed information below, where we are happy to invite many domain experts as our speakers! Please join us if you are interested in Privacy or Graph Machine Learning!
Speakers: Chuan Guo (Meta), Kamalika Chaudhuri (UCSD), Raman Arora (JHU), Wanrong Zhang (Harvard)
Speakers: Santiago Segarra (Rice), Ziang Chen (MIT), Hanghang Tong (UIUC), Jiliang Tang (MSU)
2024/05: Our paper "Machine Unlearning of Pre-trained Large Language Models" is accepted by ACL 2024 as the main paper [arXiv, code]! Kudos to Jin and Xiang for leading this project!
2024/04: I gave a talk at Google about "Langevin Unlearning".
2024/04: Our project "Privacy-preserving Machine Learning on Graphs" got funded! Many thanks to NSF! I really learned a lot from Prof. Pan Li, Prof. Olgcia Milenkovic, and Prof. Kamalika Chaudhuri during this process, and look forward to future collaborations.
2024/04: Our paper "Langevin Unlearning" is accepted by the ICLR 2024 PrivML workshop as the spotlight presentation! [arXiv (long version)]. Feel free to also check out "Stochastic Gradient Langevin Unlearning" for improved results under the convexity assumption [arXiv].
2024/03: I gave an invited talk about machine unlearning at CISS 2024 at Princeton.
2024/02: I gave a talk "Machine Unlearning: Current Challenges and Beyond" at the CSIP Seminar at GaTech.
2024/01: Our paper "Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning" is accepted by TheWebConf 2024 [arXiv]. Congrats to Frank and Gorden who lead this project!
2024/01: Our paper "Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls" is accepted by TMLR [TMLR]! Congrats to all collaborators Saurav, Jin, Chao, and Professor Milenkovic.
2023/09: Our paper "Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection" is accepted by NeurIPS 2023 [arXiv, code]!
2023/08: Start my Postdoc at GaTech in Atlanta.
2023/05: Our paper "Representer Point Selection for Explaining Regularized High-dimensional Models" is accepted by ICML 2023 [arXiv]! Big congrats to Che-Ping who leads this project!
2023/05: Our paper "PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation" is accepted by ICML 2023! [arXiv, code]
2023/01: Our paper "Unlearning Nonlinear Graph Classifiers in the Limited Training Data Regime" is accepted by TheWebConf 2023 (365/1900, 19.2%. a.k.a. WWW)! [arXiv, code]
2023/01: Our paper "Efficient Model Updates for Approximate Unlearning of Graph-Structured Data" is accepted by ICLR 2023! Check our previous NeurIPS Workshop version [arXiv, code] and stay tuned for the camera-ready version!
2022/11: Our journal paper "Provably Accurate and Scalable Linear Classifiers in Hyperbolic Spaces" has been accepted by KAIS! This is a journal extension of our previous ICDM paper about theories of linear classifications in hyperbolic spaces. You may find our draft on [arXiv].
2022/11: I passed my Ph.D. final exam!
2022/10: Our paper "Certified Graph Unlearning" will be presented in NeurIPS 2022 GLFrontiers Workshop! You may check our draft on [arXiv] and stay tuned for a refined camera-ready version.
2022/05: I start my applied scientist internship at Amazon again!
2022/05: Our paper "HyperAid: Denoising in hyperbolic spaces for tree-fitting and hierarchical clustering" has been accepted by KDD 2022 (research track) as a full paper! (254/1695, 15%)
2022/04: Our paper "Small-sample estimation of the mutational support and distribution of SARS-CoV-2" has been accepted by TCBB Journal (IEEE/ACM Transactions on Computational Biology and Bioinformatics)! Big congrats to Vishal who leads this project! You can find an earlier version of it here [medRxiv].
2022/01: Two papers got accepted by ICLR 2022!
"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction" We improve general graph learning tasks with raw data (such as text)!
"You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks" We propose an unified framework for hypergraph neural networks, with connection to deep learning in set functions such as DeepSet and SetTransformer!
2021/11: Our paper "Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction" has achieved rank-1 with huge improvement in performance on 3 datasets of OGB leaderboard!
2021/09: Our paper "Highly Scalable and Provably Accurate Classification in Poincare Balls" has been accepted by ICDM 2021 as a regular paper! (98/990, 9.9%)
2021/08: I receive Amazon Post Internship Fellowship according to my internship performance this summer! Big thanks to the help from my collaborators.
2021/08: Our paper "Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs" has been accepted by ITW 2021!
2021/06: I start my applied scientist internship at Amazon!
2021/04: Our paper "Support Estimation with Sampling Artifacts and Errors" has been accepted by ISIT 2021!
2021/01: Our paper "Adaptive Universal Generalized PageRank Graph Neural Network" has been accepted by ICLR 2021! Our code can be found at github.
2020/12: I gave a talk on my recent researches "Learning on graphs: from algorithmics approaches to graph neural networks" at National Taiwan University! Main references: GPR and GPR-GNN.
2020/12: Personal website launch.