Challenges of Trustworthy Federated Learning: What's Done, Current Trends and Remaining Work
This is an incremental review that addresses the problem of ensuring trustworthy AI in federated learning for researchers and practitioners in sensitive domains.
The paper systematically analyzes the challenges of aligning Federated Learning with Trustworthy AI requirements, focusing on obstacles due to its distributed nature and providing a review of existing work, trends, and remaining gaps.
In recent years, the development of Trustworthy Artificial Intelligence (TAI) has emerged as a critical objective in the deployment of AI systems across sensitive and high-risk domains. TAI frameworks articulate a comprehensive set of ethical, legal, and technical requirements to ensure that AI technologies are aligned with human values, rights, and societal expectations. Among the various AI paradigms, Federated Learning (FL) presents a promising solution to pressing privacy concerns. However, aligning FL with the rest of the requirements of TAI presents a series of challenges, most of which arise from its inherently distributed nature. In this work, we adopt the requirements TAI as a guiding structure to systematically analyze the challenges of adapting FL to TAI. Specifically, we classify and examine the key obstacles to aligning FL with TAI, providing a detailed exploration of what has been done, the trends, and the remaining work within each of the identified challenges.