SparsyFed: Sparse Adaptive Federated Training

• URL: http://arxiv.org/abs/2504.05153v1
• Date: Mon, 07 Apr 2025 14:57:02 GMT
• Title: SparsyFed: Sparse Adaptive Federated Training
• Authors: Adriano Guastella, Lorenzo Sani, Alex Iacob, Alessio Mora, Paolo Bellavista, Nicholas D. Lane,
• Abstract summary: This paper presents SparsyFed, a practical federated sparse training method.<n>We show that SparsyFed simultaneously can produce 95% sparse models, with negligible degradation in accuracy.
• Score: 13.001548634185514
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Sparse training is often adopted in cross-device federated learning (FL) environments where constrained devices collaboratively train a machine learning model on private data by exchanging pseudo-gradients across heterogeneous networks. Although sparse training methods can reduce communication overhead and computational burden in FL, they are often not used in practice for the following key reasons: (1) data heterogeneity makes it harder for clients to reach consensus on sparse models compared to dense ones, requiring longer training; (2) methods for obtaining sparse masks lack adaptivity to accommodate very heterogeneous data distributions, crucial in cross-device FL; and (3) additional hyperparameters are required, which are notably challenging to tune in FL. This paper presents SparsyFed, a practical federated sparse training method that critically addresses the problems above. Previous works have only solved one or two of these challenges at the expense of introducing new trade-offs, such as clients' consensus on masks versus sparsity pattern adaptivity. We show that SparsyFed simultaneously (1) can produce 95% sparse models, with negligible degradation in accuracy, while only needing a single hyperparameter, (2) achieves a per-round weight regrowth 200 times smaller than previous methods, and (3) allows the sparse masks to adapt to highly heterogeneous data distributions and outperform all baselines under such conditions.

Related papers

• Client Selection in Federated Learning with Data Heterogeneity and Network Latencies [19.161254709653914]
  Federated learning (FL) is a distributed machine learning paradigm where multiple clients conduct local training based on their private data, then the updated models are sent to a central server for global aggregation.<n>In this paper, we propose two novel theoretically optimal client selection schemes that handle both these heterogeneities.
  arXiv  Detail & Related papers  (2025-04-02T17:31:15Z)
• Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding [21.76802204235636]
  We propose representation encoding-based federated meta-learning (REFML) for few-shot fault diagnosis. REFML harnesses the inherent generalization among training clients, effectively transforming it into an advantage for out-of-distribution. It achieves an increase in accuracy by 2.17%-6.50% when tested on unseen working conditions of the same equipment type and 13.44%-18.33% when tested on totally unseen equipment types.
  arXiv  Detail & Related papers  (2023-10-13T10:48:28Z)
• Communication-Efficient Federated Learning via Regularized Sparse Random Networks [21.491346993533572]
  This work presents a new method for enhancing communication efficiency in Federated Learning. In this setting, a binary mask is optimized instead of the model weights, which are kept fixed. S sparse binary masks are exchanged rather than the floating point weights in traditional federated learning.
  arXiv  Detail & Related papers  (2023-09-19T14:05:12Z)
• Efficient Personalized Federated Learning via Sparse Model-Adaptation [47.088124462925684]
  Federated Learning (FL) aims to train machine learning models for multiple clients without sharing their own private data. We propose pFedGate for efficient personalized FL by adaptively and efficiently learning sparse local models. We show that pFedGate achieves superior global accuracy, individual accuracy and efficiency simultaneously over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-04T12:21:34Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• 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)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Sparsity Winning Twice: Better Robust Generalization from More Efficient Training [94.92954973680914]
  We introduce two alternatives for sparse adversarial training: (i) static sparsity and (ii) dynamic sparsity. We find both methods to yield win-win: substantially shrinking the robust generalization gap and alleviating the robust overfitting. Our approaches can be combined with existing regularizers, establishing new state-of-the-art results in adversarial training.
  arXiv  Detail & Related papers  (2022-02-20T15:52:08Z)
• 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)
• Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees [115.08148491584997]
  We present the first theoretically grounded distributed methods for solving variational inequalities and saddle point problems using compressed communication: MASHA1 and MASHA2. New algorithms support bidirectional compressions, and also can be modified for setting with batches and for federated learning with partial participation of clients.
  arXiv  Detail & Related papers  (2021-10-07T10:04:32Z)

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.