基于 Gossip 的去中心化排名聚合：收敛性与鲁棒性

View PDF HTML (experimental)

Abstract:The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originating in social choice theory, have been documented in the literature, offering theoretical guarantees in a centralized setting, \textit{i.e.}, when all the ranking data to be aggregated can be brought together in a single computing unit. For many technologies (\textit{e.g.} peer-to-peer networks, IoT, multi-agent systems), extending the ability to calculate consensus rankings with guarantees of convergence and resilience to potential contamination in a decentralized setting, when preference data is initially distributed across a communicating network, remains a major methodological challenge. Indeed, in recent years, the literature on decentralized computation has mainly focused on computing or optimizing statistics such as arithmetic means using gossip algorithms. The purpose of this article is precisely to study how to achieve reliable and resilient consensus on collective rankings in a decentralized setting, thereby raising new questions, robustness to corrupted nodes, and scalability through reduced communication costs in particular. The approach proposed and analyzed here relies on the robustness guarantees offered by random gossip communication, which allows autonomous agents to compute a global ranking consensus using local interactions only, without coordination or a central authority.

Comments:	33 pages
Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
Cite as:	arXiv:2602.22847 [cs.LG]
	(or arXiv:2602.22847v3 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2602.22847 arXiv-issued DOI via DataCite

Submission history

From: Kerrian Le Caillec [view email]
[v1] Thu, 26 Feb 2026 10:37:23 UTC (331 KB)
[v2] Wed, 13 May 2026 14:53:10 UTC (680 KB)
[v3] Mon, 9 Nov 2026 20:39:47 UTC (700 KB)