去中心化学习的规模效应：客户端数量、数据分配与拓扑演化如何耦合

View PDF HTML (experimental)

Abstract:Scaling decentralized learning changes not only the number of clients $N$, but also the dynamics of information propagation and consensus. We argue that the effect of increasing $N$ cannot be understood in isolation, because data allocation, topology-dependent mixing, and communication capacity may change simultaneously. We study these coupled effects on CIFAR-10 with $N\in\{10,50,100,200\}$, comparing a degree-two Ring, a Static Random graph, and Local-First Heuristic Evolution (LFHE), a locally adaptive topology process based on friend-of-friend discovery. The Ring provides an analytically transparent failure mode: its Metropolis spectral gap decays as $\Theta(N^{-2})$, implying progressively slower contraction of model disagreement as the population grows. Experiments show that holding the nominal local dataset size fixed substantially reduces the apparent population penalty observed when a fixed total dataset is divided among more clients. The remaining degradation depends strongly on communication structure: Ring enters a high-disagreement regime, whereas Static Random and LFHE remain close to consensus. Increasing LFHE's degree threshold further improves accuracy and consensus, but at a substantially higher model-transmission cost. These results show that decentralized scaling is governed by coupled learning and communication dynamics, rather than by the number of clients alone.

Comments:	11 pages, 6 figures. Accepted as a poster at DynaFront @ NeurIPS 2026
Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.05476 [cs.LG]
	(or arXiv:2610.05476v2 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.05476 arXiv-issued DOI via DataCite

Submission history

From: Yin-Kuan Liang [view email]
[v1] Sun, 4 Oct 2026 19:34:43 UTC (1,815 KB)
[v2] Thu, 8 Oct 2026 11:36:03 UTC (1,817 KB)