NAN YANG

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

Can we trust the attribution method?

Conceptual Archetype Decomposition for Interpretable and Generalizable Model Decisions

C2MF: Consistent and Concept-Unified Matrix Factorization for Interpretable and Robust Concept Discovery

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Generalization Performance Gap Analysis between Centralized and Federated Learning: How to Bridge this Gap?

SSLA: A Generalized Attribution Method for Interpreting Self-Supervised Learning without Downstream Task Dependency