Haozhao Wang

Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement

2023 · arXiv (Cornell University)

This paper investigates a new, practical, but challenging problem named Non-exemplar Online Class-incremental continual Learning (NO-CL), which aims to preserve the discernibility of base classes without buffering data examples and efficiently learn novel classes continuously …

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

2024 · arXiv (Cornell University)

By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Federated Learning. Although Scaffold achieves …