← Search

Dawood Wasif

2 accepted papers

2026

Explainable Federated Learning via Global–Local Attribution Alignment

ICML 2026poster

Federated learning enables on-device training without centralizing data, yet existing systems still struggle to provide explanations that are both locally faithful and globally consistent under strict privacy and bandwidth constraints. Prior approaches either keep explanations siloed across clients,…

Cited by 0SourceScholar
2026

RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility

ICLR 2026poster

Federated Learning (FL) has gained prominence in machine learning applications across critical domains, offering collaborative model training without centralized data aggregation. However, FL frameworks that protect privacy often sacrifice fairness and reliability; differential privacy reduces data…

Cited by 0SourceScholar