A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning
For federated learning practitioners in multi-stakeholder environments, this work provides a scalable solution to enforce strategic, regulatory, or competitive client exclusion, addressing a previously overlooked gap.
This paper introduces a taxonomy of client-level disagreements in federated learning and proposes a multi-track resolution strategy that ensures strict client exclusion. The method achieves negligible server-side overhead (<1 ms per round) and effectively handles permanent, temporal, and overlapping disagreement patterns across 34 scenarios.
Federated Learning (FL) typically assumes unconditional collaboration, a premise that overlooks the complexities of real-world, multi-stakeholder environments in which clients may need to exclude one another for strategic, regulatory, or competitive reasons. This paper addresses this gap, which we term 'client-level disagreements,' by first introducing a taxonomy of such scenarios. We then propose a robust, multi-track resolution strategy that guarantees strict client exclusion by creating and managing isolated model update paths ('tracks'), thereby preventing the cross-contamination and unfairness issues present in naive strategies. Through an empirical evaluation of our custom simulation system across 34 scenarios using the MNIST and N-CMAPSS datasets, we validate that our approach correctly handles permanent, temporal, and overlapping disagreement patterns. Our scalability analysis reveals the server-side resolution algorithm's overhead is negligible (<1 ms per round) even under heavy load. The primary scalability constraint is the client-side training load from participating in multiple tracks, a cost that we show can be effectively mitigated by a submodel reuse strategy. This work presents a scalable and architecturally sound method for managing client-level disagreements, and enhances the practical applicability of FL in settings where policy compliance and strategic control are non-negotiable.