Fast-Convergent Federated Learning with Adaptive Weighting

• URL: http://arxiv.org/abs/2012.00661v2
• Date: Tue, 6 Apr 2021 01:45:41 GMT
• Title: Fast-Convergent Federated Learning with Adaptive Weighting
• Authors: Hongda Wu, Ping Wang
• Abstract summary: Federated learning (FL) enables resource-constrained edge nodes to collaboratively learn a global model under the orchestration of a central server. We propose Federated Adaptive Weighting (FedAdp) algorithm that aims to accelerate model convergence under the presence of nodes with non-IID dataset. We show that FL training with FedAdp can reduce the number of communication rounds by up to 54.1% on MNIST dataset and up to 45.4% on FashionMNIST dataset.
• Score: 6.040848035935873
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Federated learning (FL) enables resource-constrained edge nodes to collaboratively learn a global model under the orchestration of a central server while keeping privacy-sensitive data locally. The non-independent-and-identically-distributed (non-IID) data samples across participating nodes slow model training and impose additional communication rounds for FL to converge. In this paper, we propose Federated Adaptive Weighting (FedAdp) algorithm that aims to accelerate model convergence under the presence of nodes with non-IID dataset. We observe the implicit connection between the node contribution to the global model aggregation and data distribution on the local node through theoretical and empirical analysis. We then propose to assign different weights for updating the global model based on node contribution adaptively through each training round. The contribution of participating nodes is first measured by the angle between the local gradient vector and the global gradient vector, and then, weight is quantified by a designed non-linear mapping function subsequently. The simple yet effective strategy can reinforce positive (suppress negative) node contribution dynamically, resulting in communication round reduction drastically. Its superiority over the commonly adopted Federated Averaging (FedAvg) is verified both theoretically and experimentally. With extensive experiments performed in Pytorch and PySyft, we show that FL training with FedAdp can reduce the number of communication rounds by up to 54.1% on MNIST dataset and up to 45.4% on FashionMNIST dataset, as compared to FedAvg algorithm.

Related papers

• FedEP: Tailoring Attention to Heterogeneous Data Distribution with Entropy Pooling for Decentralized Federated Learning [8.576433180938004]
  This paper proposes a novel DFL aggregation algorithm, Federated Entropy Pooling (FedEP) FedEP mitigates the client drift problem by incorporating the statistical characteristics of local distributions instead of any actual data. Experiments have demonstrated that FedEP can achieve faster convergence and show higher test performance than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-10T07:39:15Z)
• Harnessing Increased Client Participation with Cohort-Parallel Federated Learning [2.9593087583214173]
  Federated Learning (FL) is a machine learning approach where nodes collaboratively train a global model. We introduce Cohort-Parallel Federated Learning (CPFL), a novel learning approach where each cohort independently trains a global model. CPFL with four cohorts, non-IID data distribution, and CIFAR-10 yields a 1.9$times$ reduction in train time and a 1.3$times$ reduction in resource usage.
  arXiv  Detail & Related papers  (2024-05-24T15:34:09Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization [23.340237814344377]
  Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data. We introduce FeDEQ, a novel FL framework that incorporates deep equilibrium learning and consensus optimization to harness compact global data representations for efficient personalization. We show that FeDEQ matches the performance of state-of-the-art personalized FL methods, while significantly reducing communication size by up to 4 times and memory footprint by 1.5 times during training.
  arXiv  Detail & Related papers  (2023-09-27T13:48:12Z)
• Distributed Learning over Networks with Graph-Attention-Based Personalization [49.90052709285814]
  We propose a graph-based personalized algorithm (GATTA) for distributed deep learning. In particular, the personalized model in each agent is composed of a global part and a node-specific part. By treating each agent as one node in a graph the node-specific parameters as its features, the benefits of the graph attention mechanism can be inherited.
  arXiv  Detail & Related papers  (2023-05-22T13:48:30Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training [60.892342868936865]
  Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. We propose a data heterogeneous-robust FL approach, FedGSP, to address this challenge. We show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-31T03:15:28Z)
• Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data [6.040848035935873]
  Federated Learning (FL) is a distributed learning paradigm that enables a large number of resource-limited nodes to collaboratively train a model without data sharing. We proposed Optimal Aggregation algorithm for better aggregation, which finds out the optimal subset of local updates of participating nodes in each global round. We also proposed a Probabilistic Node Selection framework (FedPNS) to dynamically change the probability for each node to be selected.
  arXiv  Detail & Related papers  (2021-05-14T20:56:09Z)
• Bayesian Graph Neural Networks with Adaptive Connection Sampling [62.51689735630133]
  We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs.
  arXiv  Detail & Related papers  (2020-06-07T07:06:35Z)

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.