analiza aiqbench
This research advances decentralized machine learning by proposing a method to infer task dependencies directly from distributed data without assuming a known graph structure. The approach combines Gaussian Markov random field priors with stochastic gradient iterates to enable cooperative multitask diffusion, offering theoretical guarantees on estimation error and performance improvement over non-cooperative baselines. For practitioners in federated or edge AI settings, this work provides a robust framework for handling unknown inter-task relationships in heterogeneous networks.
Decentralized Multitask Learning over Learned Task Graphs
arXiv:2608.26989v1 Announce Type: new Abstract: This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data. We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic gradient iterates, and subsequently exploits the learned graph to enable cooperative multitask diffusion learning. This framework is motivated by a Gaussian Markov random field prior, which gives rise to a decentralized maximum likelihood estimator for the graph Laplacian. The analysis quantifies the Laplacian estimation error and its propagation to the steady-state performance of the multitask diffusion recursion, and introduces a topology sensitivity index to capture the effect of network heterogeneity. Simulation results corroborate the theoretical findings and demonstrate that cooperation enabled by the learned task graph significantly improves performance over non-cooperative learning, while approaching the true-graph baseline when the estimation stepsize is sufficiently small.
Abstract:This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data. We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic gradient iterates, and subsequently exploits the learned graph to enable cooperative multitask diffusion learning. This framework is motivated by a Gaussian Markov random field prior, which gives rise to a decentralized maximum likelihood estimator for the graph Laplacian. The analysis quantifies the Laplacian estimation error and its propagation to the steady-state performance of the multitask diffusion recursion, and introduces a topology sensitivity index to capture the effect of network heterogeneity. Simulation results corroborate the theoretical findings and demonstrate that cooperation enabled by the learned task graph significantly improves performance over non-cooperative learning, while approaching the true-graph baseline when the estimation stepsize is sufficiently small.
Machine Learning (cs.LG); Signal Processing (eess.SP); Systems and Control (eess.SY)
arXiv:2608.26989 [cs.LG]
(or arXiv:2608.26989v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.26989 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe
How controllers from industrial machinery can coordinate multitask machine learning
Amazon Science · 30 iul. 2026
Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
arXiv · 4 aug. 2026
Communication-Aware Heterogeneous Graph Learning for Decentralized Multi-Human Multi-Robot Task Allocation
arXiv · 29 sept. 2026
FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
arXiv · 31 iul. 2026