To defend the inference attacks and mitigate the sensitive information leakages in Federated
Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy …

Recently, flat minima are proven to be effective for improving generalization and sharpness-
aware minimization (SAM) achieves state-of-the-art performance. Yet the current definition of …

To mitigate the privacy leakages and communication burdens of Federated Learning (FL),
decentralized FL (DFL) discards the central server and each client only communicates with …

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced
by attackers, is becoming increasingly critical for machine learning security and integrity …

Robust generalization aims to tackle the most challenging data distributions which are rare
in the training set and contain severe noises, ie, photon-limited corruptions. Common …

Abstract Domain generalization (DG) seeks to learn robust models that generalize well
under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not …

Sharpness-aware minimization (SAM) has well documented merits in enhancing
generalization of deep neural networks, even without sizable data augmentation. Embracing …

Fine-tuning large pretrained language models on a limited training corpus usually suffers
from poor generalization. Prior works show that the recently-proposed sharpness-aware …

The goal of continual learning (CL) is to continuously learn new tasks without forgetting
previously learned old tasks. To alleviate catastrophic forgetting, gradient projection based …

In federated learning (FL), a cluster of local clients are chaired under the coordination of the
global server and cooperatively train one model with privacy protection. Due to the multiple …