Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Decentralized Learning via Random Walk with Jumps
Zonghong Liu, Matthew Dwyer, Salim El Rouayheb
We study decentralized learning over networks where data are distributed across nodes without a central coordinator. Random walk learning is a token-based approach in which a singl…
cs.LG2025
Self-Regulating Random Walks for Resilient Decentralized Learning on Graphs
Maximilian Egger, Rawad Bitar, Ghadir Ayache +2
Consider the setting of multiple random walks (RWs) on a graph executing a certain computational task. For instance, in decentralized learning via RWs, a model is updated at each i…