The integration of Federated Learning (FL) and Multi-Task Learning (MTL) has been explored to address client heterogeneity, with Federated Multi-Task Learning (FMTL) treating each client as a distinct task. However, most existing research focuses on data heterogeneity (e.g., addressing non-IID data) rather than task heterogeneity, where clients solve fundamentally different tasks. Additionally, much of the work relies on centralized settings with a server managing the federation, leaving the more challenging domain of decentralized FMTL largely unexplored. Thus, this work bridges this gap by proposing ColNet, a framework designed for heterogeneous tasks in decentralized federated environments. ColNet partitions models into a backbone and task-specific heads, and uses adaptive clustering based on model and data sensitivity to form task-coherent client groups. Backbones are averaged within groups, and group leaders perform hyper-conflict-averse cross-group aggregation. Across datasets and federations, ColNet outperforms competing schemes under label and task heterogeneity and shows robustness to poisoning attacks.
@article{arxiv.2501.10347,
title = {ColNet: Collaborative Optimization in Decentralized Federated Multi-task Learning Systems},
author = {Chao Feng and Nicolas Fazli Kohler and Zhi Wang and Weijie Niu and Alberto Huertas Celdran and Gerome Bovet and Burkhard Stiller},
journal= {arXiv preprint arXiv:2501.10347},
year = {2025}
}