Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning

• URL: http://arxiv.org/abs/2405.09037v1
• Date: Wed, 15 May 2024 02:13:51 GMT
• Title: Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning
• Authors: Riyasat Ohib, Bishal Thapaliya, Gintare Karolina Dziugaite, Jingyu Liu, Vince Calhoun, Sergey Plis,
• Abstract summary: Salient Sparse Federated Learning (SSFL) is a streamlined approach for sparse federated learning with efficient communication. We validate SSFL's effectiveness using standard non-IID benchmarks, noting marked improvements in the sparsity--accuracy trade-offs.
• Score: 10.364508878325534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient communication. SSFL identifies a sparse subnetwork prior to training, leveraging parameter saliency scores computed separately on local client data in non-IID scenarios, and then aggregated, to determine a global mask. Only the sparse model weights are communicated each round between the clients and the server. We validate SSFL's effectiveness using standard non-IID benchmarks, noting marked improvements in the sparsity--accuracy trade-offs. Finally, we deploy our method in a real-world federated learning framework and report improvement in communication time.

Related papers

• TPFL: Tsetlin-Personalized Federated Learning with Confidence-Based Clustering [0.0]
  We propose a novel approach called Tsetlin-Personalized Federated Learning. In this way, models are grouped into clusters based on their confidence towards a specific class. Clients share only what they are confident about, resulting in the elimination of wrongful weight aggregation. Results demonstrated that TPFL performance better than baseline methods with 98.94% accuracy on MNIST, 98.52% accuracy on FashionMNIST and 91.16% accuracy on FEMNIST dataset.
  arXiv  Detail & Related papers  (2024-09-16T15:27:35Z)
• Novel clustered federated learning based on local loss [14.380553970274242]
  This paper proposes LCFL, a novel metric for evaluating data distributions in learning. It aligns with learning requirements, accurately addresses privacy concerns, and provides more accurate classification.
  arXiv  Detail & Related papers  (2024-07-12T15:37:05Z)
• SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead [75.87007729801304]
  SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. Experiments show that SpaFL improves accuracy while requiring much less communication and computing resources compared to sparse baselines.
  arXiv  Detail & Related papers  (2024-06-01T13:10:35Z)
• 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)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• SemiSFL: Split Federated Learning on Unlabeled and Non-IID Data [34.49090830845118]
  Federated Learning (FL) has emerged to allow multiple clients to collaboratively train machine learning models on their private data at the network edge. We propose a novel Semi-supervised SFL system, termed SemiSFL, which incorporates clustering regularization to perform SFL with unlabeled and non-IID client data. Our system provides a 3.8x speed-up in training time, reduces the communication cost by about 70.3% while reaching the target accuracy, and achieves up to 5.8% improvement in accuracy under non-IID scenarios.
  arXiv  Detail & Related papers  (2023-07-29T02:35:37Z)
• Stochastic Clustered Federated Learning [21.811496586350653]
  This paper proposes StoCFL, a novel clustered federated learning approach for generic Non-IID issues. In detail, StoCFL implements a flexible CFL framework that supports an arbitrary proportion of client participation and newly joined clients. The results show that StoCFL could obtain promising cluster results even when the number of clusters is unknown.
  arXiv  Detail & Related papers  (2023-03-02T01:39:16Z)
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces [59.33965805898736]
  Clustered learning has been shown to produce promising results by grouping clients into clusters. Existing FL algorithms are essentially trying to group clients together with similar distributions. Prior FL algorithms attempt similarities indirectly during training.
  arXiv  Detail & Related papers  (2022-09-21T17:37:54Z)
• FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution [7.924081556869144]
  We present a new algorithm, FLIS, which groups the clients population in clusters with jointly trainable data distributions. We present experimental results to demonstrate the benefits of FLIS over the state-of-the-art benchmarks on CIFAR-100/10, SVHN, and FMNIST datasets.
  arXiv  Detail & Related papers  (2022-08-20T22:10:48Z)
• DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training [84.81043932706375]
  We propose a novel personalized federated learning framework in a decentralized (peer-to-peer) communication protocol named Dis-PFL. Dis-PFL employs personalized sparse masks to customize sparse local models on the edge. We demonstrate that our method can easily adapt to heterogeneous local clients with varying computation complexities.
  arXiv  Detail & Related papers  (2022-06-01T02:20:57Z)
• 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)

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.