FLAT-Bench: A Federated Learning Benchmark for Adaptation and Trust Evaluation

ICLR 2026 Conference Submission18360 Authors

Keywords: Federated Learning, Trustworthiness, Adaptation, Adversarial Robustness, Generalization

TL;DR: FLAT-Bench provides a unified framework and empirical benchmark for analysing adaptation to heterogeneous clients and trust in adversarial federated learning settings.

Abstract: Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows, numerous techniques have been proposed to tackle its practical challenges. However, the lack of standardized evaluation across key dimensions hampers systematic progress and fair comparison of FL methods. In this work, we introduce FLAT-Bench, a unified framework for analyzing federated learning through two foundational dimensions: Adaptation and Trust. We provide an in-depth examination of the conceptual foundations, task formulations, and open research challenges associated with each theme. We have extensively benchmarked representative methods and datasets for adaptation to heterogeneous clients and trustworthiness in adversarial or unreliable environments. FLAT-Bench lays the groundwork for systematic and holistic evaluation of federated learning with real-world relevance. We will make our complete codebase publicly accessible and a curated repository that continuously tracks new developments and research in the FL literature.

Primary Area: datasets and benchmarks

Submission Number: 18360