DICE: Data Influence Cascade in Decentralized Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Tongtian, Li, Wenhao, Wang, Can, He, Fengxiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908442304708608
author Zhu, Tongtian
Li, Wenhao
Wang, Can
He, Fengxiang
author_facet Zhu, Tongtian
Li, Wenhao
Wang, Can
He, Fengxiang
contents Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through peer-to-peer networks, accommodating the exponentially increasing demands. However, proper incentives are still in absence, considerably discouraging participation. Our vision is that a fair incentive mechanism relies on fair attribution of contributions to participating nodes, which faces non-trivial challenges arising from the localized connections making influence ``cascade'' in a decentralized network. To overcome this, we design the first method to estimate \textbf{D}ata \textbf{I}nfluence \textbf{C}ascad\textbf{E} (DICE) in a decentralized environment. Theoretically, the framework derives tractable approximations of influence cascade over arbitrary neighbor hops, suggesting the influence cascade is determined by an interplay of data, communication topology, and the curvature of loss landscape. DICE also lays the foundations for applications including selecting suitable collaborators and identifying malicious behaviors. Project page is available at https://raiden-zhu.github.io/blog/2025/DICE/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06931
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DICE: Data Influence Cascade in Decentralized Learning
Zhu, Tongtian
Li, Wenhao
Wang, Can
He, Fengxiang
Machine Learning
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Social and Information Networks
Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through peer-to-peer networks, accommodating the exponentially increasing demands. However, proper incentives are still in absence, considerably discouraging participation. Our vision is that a fair incentive mechanism relies on fair attribution of contributions to participating nodes, which faces non-trivial challenges arising from the localized connections making influence ``cascade'' in a decentralized network. To overcome this, we design the first method to estimate \textbf{D}ata \textbf{I}nfluence \textbf{C}ascad\textbf{E} (DICE) in a decentralized environment. Theoretically, the framework derives tractable approximations of influence cascade over arbitrary neighbor hops, suggesting the influence cascade is determined by an interplay of data, communication topology, and the curvature of loss landscape. DICE also lays the foundations for applications including selecting suitable collaborators and identifying malicious behaviors. Project page is available at https://raiden-zhu.github.io/blog/2025/DICE/.
title DICE: Data Influence Cascade in Decentralized Learning
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Social and Information Networks
url https://arxiv.org/abs/2507.06931