Research Fellow
NExT++ Lab
School of Computing
National University of Singapore
Email: an.zhang3.14 at gmail.com
• Google Scholar Page • GitHub Page
Biography
I am a Research Fellow in National University of Singapore, where I am a member of NExT++ Lab, supervised by Prof Tat-Seng Chua. With my colleagues, students, and collaborators, we strive to develop trustworthy and Robustness of AI algorithms with better interpretability, generalization, and causality of AI. Our research is motivated by, and contributes to, applications in information retrieval (e.g., collaborative filtering), data mining (e.g., graph pre-training), and causality (e.g., causal inference and causal discovery). My work has several publications in top-tier conferences (e.g., NeurIPS, WWW, KDD, ICML, ICLR, SIGIR) and journals (e.g., TPAMI, TOIS). Moreover, I have served as the PC member for top-tier conferences including NeurIPS, SIGIR, ICLR, KDD, EMNLP, WWW, AAAI, ICML, and WSDM.
Prospective Intern Students
I am looking for highly motivated interns (visiting Ph.D., master, and undergraduate students) to work together on the trustworthiness and robustness of graphs, especially pre-training, interpretability, generalization, and causality, and their applications in real-world scenarios. Please feel free to send me your CV and transcripts, if you have interest. We are also actively looking for opportunities in research, partnership and commercialization in exciting data science projects.
News and Highlights
Robust Collaborative Filtering to Popularity Distribution Shift.
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction.
Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss.
Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis.
Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules.
Redundancy-aware Transformer for Video Question Answering.
Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation.
Discovering Dynamic Causal Space for DAG Structure Learning.
Invariant Collaborative Filtering to Popularity Distribution Shift.
Boosting Causal Discovery via Adaptive Sample Reweighting.
Cooperative Explanations of Graph Neural Networks.
Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering.
Let invariant Rationale Discovery inspire Graph Contrastive Learning.
CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation.
Reinforced Causal Explainer for Graph Neural Networks.
Discovering invariant rationales for graph neural networks.
Professional Services
Honors and Awards
Background
Supervisor: Prof Tat-Seng Chua & Prof Zhenkai Liang
Supervisor: Prof Tat-Seng Chua
Supervisor: Prof Zehua Chen
Supervisor: Prof Jinde Cao & Prof Wenwu Yu