Leveraging Function Space Aggregation for Federated Learning at Scale

• URL: http://arxiv.org/abs/2311.10291v2
• Date: Sat, 17 Feb 2024 00:05:55 GMT
• Title: Leveraging Function Space Aggregation for Federated Learning at Scale
• Authors: Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite
• Abstract summary: We propose a new algorithm, FedFish, that aggregates local approximations to the functions learned by clients. We evaluate FedFish on realistic, large-scale cross-device benchmarks.
• Score: 20.866482460590973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The federated learning paradigm has motivated the development of methods for aggregating multiple client updates into a global server model, without sharing client data. Many federated learning algorithms, including the canonical Federated Averaging (FedAvg), take a direct (possibly weighted) average of the client parameter updates, motivated by results in distributed optimization. In this work, we adopt a function space perspective and propose a new algorithm, FedFish, that aggregates local approximations to the functions learned by clients, using an estimate based on their Fisher information. We evaluate FedFish on realistic, large-scale cross-device benchmarks. While the performance of FedAvg can suffer as client models drift further apart, we demonstrate that FedFish is more robust to longer local training. Our evaluation across several settings in image and language benchmarks shows that FedFish outperforms FedAvg as local training epochs increase. Further, FedFish results in global networks that are more amenable to efficient personalization via local fine-tuning on the same or shifted data distributions. For instance, federated pretraining on the C4 dataset, followed by few-shot personalization on Stack Overflow, results in a 7% improvement in next-token prediction by FedFish over FedAvg.

Related papers

• 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)
• Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients [30.135431295658343]
  Federated learning (FL) aims to learn a common global model without exchanging or transferring the data that are stored locally at different clients. In this paper, we propose an efficient federated learning (AFL) framework called DeFedAvg. DeFedAvg is the first AFL algorithm that achieves the desirable linear speedup property, which indicates its high scalability.
  arXiv  Detail & Related papers  (2024-02-17T05:22:46Z)
• FedImpro: Measuring and Improving Client Update in Federated Learning [77.68805026788836]
  Federated Learning (FL) models often experience client drift caused by heterogeneous data. We present an alternative perspective on client drift and aim to mitigate it by generating improved local models.
  arXiv  Detail & Related papers  (2024-02-10T18:14:57Z)
• 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)
• FedCME: Client Matching and Classifier Exchanging to Handle Data Heterogeneity in Federated Learning [5.21877373352943]
  Data heterogeneity across clients is one of the key challenges in Federated Learning (FL) We propose a novel FL framework named FedCME by client matching and classifier exchanging. Experimental results demonstrate that FedCME performs better than FedAvg, FedProx, MOON and FedRS on popular federated learning benchmarks.
  arXiv  Detail & Related papers  (2023-07-17T15:40:45Z)
• FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation [95.85026305874824]
  We introduce a data-driven approach called FedSkip to improve the client optima by periodically skipping federated averaging and scattering local models to the cross devices. We conduct extensive experiments on a range of datasets to demonstrate that FedSkip achieves much higher accuracy, better aggregation efficiency and competing communication efficiency.
  arXiv  Detail & Related papers  (2022-12-14T13:57:01Z)
• FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction [48.85303253333453]
  Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. We propose a novel federated learning algorithm with local drift decoupling and correction (FedDC) Our FedDC only introduces lightweight modifications in the local training phase, in which each client utilizes an auxiliary local drift variable to track the gap between the local model parameter and the global model parameters. Experiment results and analysis demonstrate that FedDC yields expediting convergence and better performance on various image classification tasks.
  arXiv  Detail & Related papers  (2022-03-22T14:06:26Z)
• 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)
• FedBN: Federated Learning on Non-IID Features via Local Batch Normalization [23.519212374186232]
  The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data. We propose an effective method that uses local batch normalization to alleviate the feature shift before averaging models. The resulting scheme, called FedBN, outperforms both classical FedAvg and the state-of-the-art for non-iid data.
  arXiv  Detail & Related papers  (2021-02-15T16:04:10Z)
• FedNS: Improving Federated Learning for collaborative image classification on mobile clients [22.980223900446997]
  Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model. We propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. We show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.
  arXiv  Detail & Related papers  (2021-01-20T06:45:46Z)

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.