On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning

ICLROral2026

Authors
Tongtian Zhu, Tianyu Zhang, Mingze Wang, Zhanpeng Zhou, Can Wang
Affiliation
Zhejiang University
Venue
ICLR 2026
Track
Oral

TL;DR

We discover and theoretically explain why and when a single global parameter merging in decentralized learning can recover the performance of federated learning, even in highly heterogeneous and communication-constrained environments.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

federated learning

Related ICLR papers

← All ICLR 2026 Oral papers · Browse the whole archive