Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity

• URL: http://arxiv.org/abs/2504.17520v1
• Date: Thu, 24 Apr 2025 13:02:54 GMT
• Title: Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity
• Authors: Zhuojun Tian, Zhaoyang Zhang, Yiwei Li, Mehdi Bennis,
• Abstract summary: We propose a distributed strong lottery ticket hypothesis (TH), based on which a communication-efficient personalized learning algorithm is developed.<n>In the proposed method, each local model is represented as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning.<n>We provide a theoretical proof for the DSLTH, establishing it as the foundation of the proposed method.
• Score: 40.64395367773766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a distributed strong lottery ticket hypothesis (DSLTH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represented as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning. The local model is learned by updating and fusing the personalized binary masks while the real-valued parameters are fixed among different agents. To further reduce the complexity of hardware implementation, we incorporate a group sparse regularization term in the loss function, enabling the learned local model to achieve structured sparsity. Then, a binary mask aggregation algorithm is designed by introducing an intermediate aggregation tensor and adding a personalized fine-tuning step in each iteration, which constrains model updates towards the local data distribution. The proposed method effectively leverages the relativity among agents while meeting personalized requirements in heterogeneous node conditions. We also provide a theoretical proof for the DSLTH, establishing it as the foundation of the proposed method. Numerical simulations confirm the validity of the DSLTH and demonstrate the effectiveness of the proposed algorithm.

Related papers

• A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data [0.0]
  This paper proposes a novel method to improve the quality of local updates and enhance the robustness of the global model.<n>The proposed merging algorithm reduces the number of local nodes while maintaining the accuracy of the global model.<n> Experimental results on the MNIST dataset under simulated federated learning scenarios demonstrate the method's effectiveness.
  arXiv  Detail & Related papers  (2025-01-19T16:59:07Z)
• Vanishing Variance Problem in Fully Decentralized Neural-Network Systems [0.8212195887472242]
  Federated learning and gossip learning are emerging methodologies designed to mitigate data privacy concerns. Our research introduces a variance-corrected model averaging algorithm. Our simulation results demonstrate that our approach enables gossip learning to achieve convergence efficiency comparable to that of federated learning.
  arXiv  Detail & Related papers  (2024-04-06T12:49:20Z)
• FedSym: Unleashing the Power of Entropy for Benchmarking the Algorithms for Federated Learning [1.4656078321003647]
  Federated learning (FL) is a decentralized machine learning approach where independent learners process data privately. We study the currently popular data partitioning techniques and visualize their main disadvantages. We propose a method that leverages entropy and symmetry to construct 'the most challenging' and controllable data distributions.
  arXiv  Detail & Related papers  (2023-10-11T18:39:08Z)
• FedAgg: Adaptive Federated Learning with Aggregated Gradients [1.5653612447564105]
  We propose an adaptive FEDerated learning algorithm called FedAgg to alleviate the divergence between the local and average model parameters and obtain a fast model convergence rate. We show that our framework is superior to existing state-of-the-art FL strategies for enhancing model performance and accelerating convergence rate under IID and Non-IID datasets.
  arXiv  Detail & Related papers  (2023-03-28T08:07:28Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Model Fusion with Kullback--Leibler Divergence [58.20269014662046]
  We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors.
  arXiv  Detail & Related papers  (2020-07-13T03:27:45Z)
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data [66.78671826743884]
  The distributionally robust optimization framework is considered for training a parametric model. The objective is to endow the trained model with robustness against adversarially manipulated input data. Proposed algorithms offer robustness with little overhead.
  arXiv  Detail & Related papers  (2020-07-07T18:25:25Z)
• Pre-Trained Models for Heterogeneous Information Networks [57.78194356302626]
  We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network. PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.
  arXiv  Detail & Related papers  (2020-07-07T03:36:28Z)
• FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data [59.50904660420082]
  Federated Learning (FL) has become a popular paradigm for learning from distributed data. To effectively utilize data at different devices without moving them to the cloud, algorithms such as the Federated Averaging (FedAvg) have adopted a "computation then aggregation" (CTA) model.
  arXiv  Detail & Related papers  (2020-05-22T23:07:42Z)

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.