← Search

Wenjun Ding

2 accepted papers

2025

How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?

AAAI 2025technical

Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, they primarily focus on convergence performance and overlook generalization. Generalization is crucial for evaluating alg…

Cited by 0SourcePDFScholar
2025

On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels

NeurIPS 2025poster

Meta-learning has achieved significant advancements, with generalization emerging as a key metric for evaluating meta-learning algorithms. While recent studies have mainly focused on training strategies, data-split methods, and tightening generalization bounds, they often ignore the impact of inner-…

Cited by 0SourceScholar