Communication-Efficient Distributionally Robust Decentralized Learning

• URL: http://arxiv.org/abs/2205.15614v1
• Date: Tue, 31 May 2022 09:00:37 GMT
• Title: Communication-Efficient Distributionally Robust Decentralized Learning
• Authors: Matteo Zecchin, Marios Kountouris, David Gesbert
• Abstract summary: Decentralized learning algorithms empower interconnected edge devices to share data and computational resources. We propose a single decentralized loop descent/ascent algorithm (ADGDA) to solve the underlying minimax optimization problem.
• Score: 23.612400109629544
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Decentralized learning algorithms empower interconnected edge devices to share data and computational resources to collaboratively train a machine learning model without the aid of a central coordinator (e.g. an orchestrating basestation). In the case of heterogeneous data distributions at the network devices, collaboration can yield predictors with unsatisfactory performance for a subset of the devices. For this reason, in this work we consider the formulation of a distributionally robust decentralized learning task and we propose a decentralized single loop gradient descent/ascent algorithm (AD-GDA) to solve the underlying minimax optimization problem. We render our algorithm communication efficient by employing a compressed consensus scheme and we provide convergence guarantees for smooth convex and non-convex loss functions. Finally, we corroborate the theoretical findings with empirical evidence of the ability of the proposed algorithm in providing unbiased predictors over a network of collaborating devices with highly heterogeneous data distributions.

Related papers

• Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration [66.43954501171292]
  We introduce Catalyst Acceleration and propose an acceleration Decentralized Federated Learning algorithm called DFedCata. DFedCata consists of two main components: the Moreau envelope function, which addresses parameter inconsistencies, and Nesterov's extrapolation step, which accelerates the aggregation phase. Empirically, we demonstrate the advantages of the proposed algorithm in both convergence speed and generalization performance on CIFAR10/100 with various non-iid data distributions.
  arXiv  Detail & Related papers  (2024-10-09T06:17:16Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Federated Learning with a Sampling Algorithm under Isoperimetry [9.990687944474738]
  Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices. We propose a communication-efficient variant of Langevinvin's sample a posteriori.
  arXiv  Detail & Related papers  (2022-06-02T08:19:03Z)
• Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis [8.863089484787835]
  We propose a distributed approximate Newton-type Newton-type training scheme, namely FedOVA, to solve the heterogeneous statistical challenge brought by heterogeneous data. FedOVA decomposes a multi-class classification problem into more straightforward binary classification problems and then combines their respective outputs using ensemble learning.
  arXiv  Detail & Related papers  (2021-10-14T17:35:24Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)
• Cross-Gradient Aggregation for Decentralized Learning from Non-IID data [34.23789472226752]
  Decentralized learning enables a group of collaborative agents to learn models using a distributed dataset without the need for a central parameter server. We propose Cross-Gradient Aggregation (CGA), a novel decentralized learning algorithm. We show superior learning performance of CGA over existing state-of-the-art decentralized learning algorithms.
  arXiv  Detail & Related papers  (2021-03-02T21:58:12Z)
• A Low Complexity Decentralized Neural Net with Centralized Equivalence using Layer-wise Learning [49.15799302636519]
  We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers) In our setup, the training data is distributed among the workers but is not shared in the training process due to privacy and security concerns. We show that it is possible to achieve equivalent learning performance as if the data is available in a single place.
  arXiv  Detail & Related papers  (2020-09-29T13:08:12Z)
• A Compressive Sensing Approach for Federated Learning over Massive MIMO Communication Systems [82.2513703281725]
  Federated learning is a privacy-preserving approach to train a global model at a central server by collaborating with wireless devices. We present a compressive sensing approach for federated learning over massive multiple-input multiple-output communication systems.
  arXiv  Detail & Related papers  (2020-03-18T05:56:27Z)
• Quantized Decentralized Stochastic Learning over Directed Graphs [52.94011236627326]
  We consider a decentralized learning problem where data points are distributed among computing nodes communicating over a directed graph. As the model size gets large, decentralized learning faces a major bottleneck that is the communication load due to each node transmitting messages (model updates) to its neighbors. We propose the quantized decentralized learning algorithm over directed graphs that is based on the push-sum algorithm in decentralized consensus optimization.
  arXiv  Detail & Related papers  (2020-02-23T18:25:39Z)
• Gradient tracking and variance reduction for decentralized optimization and machine learning [19.54092620537586]
  Decentralized methods to solve finite-sum problems are important in many signal processing and machine learning tasks. We provide a unified algorithmic framework that combines variance-reduction with gradient tracking to achieve robust performance.
  arXiv  Detail & Related papers  (2020-02-13T07:17:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.