AI RESEARCH
Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating
arXiv CS.LG
•
ArXi:2605.23424v1 Announce Type: cross In-network learning (INL) trains distributed neural modules by exchanging latent activations and backpropagated errors over a communication graph. This letter proposes Dijkstra-pruned INL (D-INL), which removes non-tree links by retaining a capacity-aware shortest-path tree rooted at the fusion node. To balance sparsity and predictive information, local routing (or aggregation) is modeled as a finite-rate stochastic gate with rate $R_g=I(Z; T