paper-with-me

Papers

Structured Cooperative Learning with Graphical Model Priors

2023-06-16 · Shuangtong Li, Tianyi Zhou, Xinmei Tian, DaCheng Tao

We study how to train personalized models for different tasks on decentralized devices with limited local data. We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical model prior to automatically coordinate mutual learning between devices. By choosing graphical models enforcing different structures, we can derive a rich class of existing and novel decentralized learning algorithms via variational inference. In particular, we show three instantiations of SCooL that adopt Dirac distribution, stochastic block model (SBM), and attention as the prior generating cooperation graphs. These EM-type algorithms alternate between updating the cooperation graph and cooperative learning of local models. They can automatically capture the cross-task correlations among devices by only monitoring their model updating in order to optimize the cooperation graph. We evaluate SCooL and compare it with existing decentralized learning methods on an extensive set of benchmarks, on which SCooL always achieves the highest accuracy of personalized models and significantly outperforms other baselines on communication efficiency. Our code is available at https://github.com/ShuangtongLi/SCooL.

📄 PDF Abstract BibTeX arXiv:2306.09595

Code (1)

shuangtongli/scool 공식 구현 pytorch

Tasks

modelStochastic Block ModelVariational Inference

Similar Papers 제목 키워드 기반

Strategic learning for disturbance rejection in multi-agent systems: Nash and Minmax in graphical games

2025-04-10 · Xinyang Wang, Martin Guay, Shimin Wang, Hongwei Zhang

This article investigates the optimal control problem with disturbance rejection for discrete-time multi-agent systems under cooperative and non-cooperative graphical games frameworks. Given the practical challenges of o…

Cooperative Graphical Models

2016-12-01 · NeurIPS 2016 12 · Josip Djolonga, Stefanie Jegelka, Sebastian Tschiatschek, Andreas Krause

We study a rich family of distributions that capture variable interactions significantly more expressive than those representable with low-treewidth or pairwise graphical models, or log-supermodular models. We call these…

Variational Inference

Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification

2019-06-01 · NeurIPS 2018 12 · Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai 외

We propose a new approach, called cooperative neural networks (CoNN), which uses a set of cooperatively trained neural networks to capture latent representations that exploit prior given independence structure. The model…

General Classificationtext-classificationText Classification

Concentration of a sparse Bayesian model with Horseshoe prior in estimating high-dimensional precision matrix

2024-06-20 · The Tien Mai

Precision matrices are crucial in many fields such as social networks, neuroscience, and economics, representing the edge structure of Gaussian graphical models (GGMs), where a zero in an off-diagonal position of the pre…

Efficient Learning of Discrete Graphical Models

2019-02-02 · NeurIPS 2020 12 · Marc Vuffray, Sidhant Misra, Andrey Y. Lokhov

Graphical models are useful tools for describing structured high-dimensional probability distributions. Development of efficient algorithms for learning graphical models with least amount of data remains an active resear…