DICE: Data Influence Cascade in Decentralized Learning
Zhu, Tongtian, Li, Wenhao, Wang, Can, He, Fengxiang
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/.
Jul-10-2025
- Country:
- Europe
- France (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Russia > Central Federal District
- Moscow Oblast > Moscow (0.04)
- Asia
- Middle East
- Jordan (0.04)
- Iraq > Basra Governorate
- Basra (0.04)
- China > Zhejiang Province
- Hangzhou (0.04)
- Middle East
- Europe
- Genre:
- Overview (1.00)
- Research Report > Promising Solution (0.34)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology:
- Information Technology
- Security & Privacy (1.00)
- Communications > Networks (1.00)
- Data Science > Data Mining (0.94)
- Artificial Intelligence
- Representation & Reasoning (1.00)
- Natural Language
- Large Language Model (1.00)
- Chatbot (0.93)
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Statistical Learning (0.68)
- Information Technology