paper-with-me

홈 › Papers

Decentralized Ranking Aggregation via Gossip: Convergence and Robustness

2026-02-26 · Kerrian Le Caillec, Anna Van Elst, Igor Colin, Stephan Clémençon arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.22847

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Asynchronous Gossip Algorithms for Rank-Based Statistical Methods

2025-09-09 · Anna Van Elst, Igor Colin, Stephan Clémençon arxiv

As decentralized AI and edge intelligence become increasingly prevalent, ensuring robustness and trustworthiness in such distributed settings has become a critical issue-especially in the presence of corrupted or adversa…

On Gossip Algorithms for Machine Learning with Pairwise Objectives

2026-03-25 · Igor Colin, Aurélien Bellet, Stephan Clémençon, Joseph Salmon arxiv

In the IoT era, information is more and more frequently picked up by connected smart sensors with increasing, though limited, storage, communication and computation abilities. Whether due to privacy constraints or to the…

Fast and Efficient Gossip Algorithms for Robust and Non-smooth Decentralized Learning

2026-01-28 · Anna van Elst, Igor Colin, Stephan Clémençon arxiv

Decentralized learning on resource-constrained edge devices demands algorithms that are communication-efficient, robust to data corruption, and lightweight in memory. State-of-the-art gossip-based methods address communi…

Vanishing Variance Problem in Fully Decentralized Neural-Network Systems

2024-04-06 · Yongding Tian, Zaid Al-Ars, Maksim Kitsak, Peter Hofstee

Federated learning and gossip learning are emerging methodologies designed to mitigate data privacy concerns by retaining training data on client devices and exclusively sharing locally-trained machine learning (ML) mode…

Federated Learning

Unified Breakdown Analysis for Byzantine Robust Gossip

2024-10-14 · Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx

In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduc…