WH
0000-0001-5674-7021 About
Dr. Huang obtained his Ph.D. degree at Faculty of Engineering and Information Technology, University of Technology Sydney .
My research intestest is deep learning theory, namely, theoretically understanding deep learning from expressivity, trainability, and generalization.
Employment
-
RIKEN Postdoctoral Researcher2021 - Present
-
University of Sydney Research Assistant2021 - 2021
Education
-
University of Technology Sydney Ph.D.2017 - 2021
Projects & Funding
Projects & funding information is unavailable.
Publications (23)
- Ensemble of Intermediate-Level Attacks to Boost Adversarial Transferability Save
- Negatively correlated ensemble against transfer adversarial attacks Save
- On the Comparison between Multi-modal and Single-modal Contrastive Learning Save
- Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization Save
- The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs Save
- Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance Save
- Global and local prompts cooperation via optimal transport for federated learning Save
- Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory Save
- DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition Save
- Single-pass contrastive learning can work for both homophilic and heterophilic graph Save