FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning

• URL: http://arxiv.org/abs/2111.11556v1
• Date: Mon, 22 Nov 2021 22:06:58 GMT
• Title: FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
• Authors: Elnur Gasanov and Ahmed Khaled and Samuel Horv\'ath and Peter Richt\'arik
• Abstract summary: Federated learning is an increasingly popular machine learning paradigm in which multiple nodes try to collaboratively learn. Standard average risk minimization of supervised learning is inadequate in handling several major constraints specific to federated learning. We introduce a new framework, FLIX, that takes into account the unique challenges brought by federated learning.
• Score: 4.492444446637857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) is an increasingly popular machine learning paradigm in which multiple nodes try to collaboratively learn under privacy, communication and multiple heterogeneity constraints. A persistent problem in federated learning is that it is not clear what the optimization objective should be: the standard average risk minimization of supervised learning is inadequate in handling several major constraints specific to federated learning, such as communication adaptivity and personalization control. We identify several key desiderata in frameworks for federated learning and introduce a new framework, FLIX, that takes into account the unique challenges brought by federated learning. FLIX has a standard finite-sum form, which enables practitioners to tap into the immense wealth of existing (potentially non-local) methods for distributed optimization. Through a smart initialization that does not require any communication, FLIX does not require the use of local steps but is still provably capable of performing dissimilarity regularization on par with local methods. We give several algorithms for solving the FLIX formulation efficiently under communication constraints. Finally, we corroborate our theoretical results with extensive experimentation.

Related papers

• Advances in APPFL: A Comprehensive and Extensible Federated Learning Framework [1.4206132527980742]
  Federated learning (FL) is a distributed machine learning paradigm enabling collaborative model training while preserving data privacy. We present the recent advances in developing APPFL, a framework and benchmarking suite for federated learning. We demonstrate the capabilities of APPFL through extensive experiments evaluating various aspects of FL, including communication efficiency, privacy preservation, computational performance, and resource utilization.
  arXiv  Detail & Related papers  (2024-09-17T22:20:26Z)
• FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data [54.81695390763957]
  Federated learning is an emerging distributed machine learning method. We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate. We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
  arXiv  Detail & Related papers  (2023-09-18T12:35:05Z)
• Communication-Efficient Decentralized Federated Learning via One-Bit Compressive Sensing [52.402550431781805]
  Decentralized federated learning (DFL) has gained popularity due to its practicality across various applications. Compared to the centralized version, training a shared model among a large number of nodes in DFL is more challenging. We develop a novel algorithm based on the framework of the inexact alternating direction method (iADM)
  arXiv  Detail & Related papers  (2023-08-31T12:22:40Z)
• Federated Gradient Matching Pursuit [17.695717854068715]
  Traditional machine learning techniques require centralizing all training data on one server or data hub. In particular, federated learning (FL) provides such a solution to learn a shared model while keeping training data at local clients. We propose a novel algorithmic framework, federated gradient matching pursuit (FedGradMP), to solve the sparsity constrained minimization problem in the FL setting.
  arXiv  Detail & Related papers  (2023-02-20T16:26:29Z)
• Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization [107.72786199113183]
  Federated learning (FL) provides a distributed learning framework for multiple participants to collaborate learning without sharing raw data. In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness.
  arXiv  Detail & Related papers  (2022-03-18T04:58:34Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)
• Communication-Efficient Hierarchical Federated Learning for IoT Heterogeneous Systems with Imbalanced Data [42.26599494940002]
  Federated learning (FL) is a distributed learning methodology that allows multiple nodes to cooperatively train a deep learning model. This paper studies the potential of hierarchical FL in IoT heterogeneous systems. It proposes an optimized solution for user assignment and resource allocation on multiple edge nodes.
  arXiv  Detail & Related papers  (2021-07-14T08:32:39Z)
• Decentralized Personalized Federated Learning for Min-Max Problems [79.61785798152529]
  This paper is the first to study PFL for saddle point problems encompassing a broader range of optimization problems. We propose new algorithms to address this problem and provide a theoretical analysis of the smooth (strongly) convex-(strongly) concave saddle point problems. Numerical experiments for bilinear problems and neural networks with adversarial noise demonstrate the effectiveness of the proposed methods.
  arXiv  Detail & Related papers  (2021-06-14T10:36:25Z)
• Practical One-Shot Federated Learning for Cross-Silo Setting [114.76232507580067]
  One-shot federated learning is a promising approach to make federated learning applicable in cross-silo setting. We propose a practical one-shot federated learning algorithm named FedKT. By utilizing the knowledge transfer technique, FedKT can be applied to any classification models and can flexibly achieve differential privacy guarantees.
  arXiv  Detail & Related papers  (2020-10-02T14:09:10Z)

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.