PFLlib: Personalized Federated Learning Algorithm Library

• URL: http://arxiv.org/abs/2312.04992v1
• Date: Fri, 8 Dec 2023 12:03:08 GMT
• Title: PFLlib: Personalized Federated Learning Algorithm Library
• Authors: Jianqing Zhang, Yang Liu, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, and Jian Cao
• Abstract summary: PFLlib is a comprehensive pFL algorithm library with an integrated evaluation platform. We implement 34 state-of-the-art FL algorithms, including 7 classic tFL algorithms and 27 pFL algorithms. PFLlib has already gained 850 stars and 199 forks on GitHub.
• Score: 27.954706790789434
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to achieve a balance between the global and personalized objectives of each client in FL settings. To foster the pFL research community, we propose PFLlib, a comprehensive pFL algorithm library with an integrated evaluation platform. In PFLlib, We implement 34 state-of-the-art FL algorithms (including 7 classic tFL algorithms and 27 pFL algorithms) and provide various evaluation environments with three statistically heterogeneous scenarios and 14 datasets. At present, PFLlib has already gained 850 stars and 199 forks on GitHub.

Related papers

• GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning [32.884949308979465]
  We propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy.
  arXiv  Detail & Related papers  (2023-08-20T14:25:31Z)
• Bayesian Federated Learning: A Survey [54.40136267717288]
  Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. The robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions. BFL has emerged as a promising approach to address these issues.
  arXiv  Detail & Related papers  (2023-04-26T03:41:17Z)
• Vertical Federated Learning: Taxonomies, Threats, and Prospects [22.487434998185773]
  Federated learning (FL) is the most popular distributed machine learning technique. FL can be divided into horizontal federated learning (HFL) and vertical federated learning (VFL) VFL is more relevant than HFL as different companies hold different features for the same set of customers. Although VFL is an emerging area of research, it is not well-established compared to HFL.
  arXiv  Detail & Related papers  (2023-02-03T05:13:40Z)
• FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings [51.09574369310246]
  Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models. We propose a novel cross-silo dataset suite focused on healthcare, FLamby, to bridge the gap between theory and practice of cross-silo FL. Our flexible and modular suite allows researchers to easily download datasets, reproduce results and re-use the different components for their research.
  arXiv  Detail & Related papers  (2022-10-10T12:17:30Z)
• pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning [42.819532536636835]
  We propose the first comprehensive pFL benchmark, pFL-Bench, for rapid, reproducible, standardized and thorough pFL evaluation. The proposed benchmark contains more than 10 datasets in diverse application domains with unified data partition and realistic heterogeneous settings. We highlight the benefits and potential of state-of-the-art pFL methods and hope pFL-Bench enables further pFL research and broad applications.
  arXiv  Detail & Related papers  (2022-06-08T02:51:59Z)
• Achieving Personalized Federated Learning with Sparse Local Models [75.76854544460981]
  Federated learning (FL) is vulnerable to heterogeneously distributed data. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. Existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. We proposeFedSpa, a novel PFL scheme that employs personalized sparse masks to customize sparse local models on the edge.
  arXiv  Detail & Related papers  (2022-01-27T08:43:11Z)
• Multi-Center Federated Learning [62.32725938999433]
  Federated learning (FL) can protect data privacy in distributed learning. It merely collects local gradients from users without access to their data. We propose a novel multi-center aggregation mechanism.
  arXiv  Detail & Related papers  (2021-08-19T12:20:31Z)
• Towards Personalized Federated Learning [20.586573091790665]
  We present a unique taxonomy dividing PFL techniques into data-based and model-based approaches. We highlight their key ideas, and envision promising future trajectories of research towards new PFL architectural design.
  arXiv  Detail & Related papers  (2021-03-01T02:45:19Z)
• PFL-MoE: Personalized Federated Learning Based on Mixture of Experts [1.8757823231879849]
  Federated learning (FL) avoids data sharing among training nodes so as to protect data privacy. PFL-MoE is a generic approach and can be instantiated by integrating existing PFL algorithms. We demonstrate the effectiveness of PFL-MoE by training the LeNet-5 and VGG-16 models on the Fashion-MNIST datasets.
  arXiv  Detail & Related papers  (2020-12-31T12:51:14Z)
• FedML: A Research Library and Benchmark for Federated Machine Learning [55.09054608875831]
  Federated learning (FL) is a rapidly growing research field in machine learning. Existing FL libraries cannot adequately support diverse algorithmic development. We introduce FedML, an open research library and benchmark to facilitate FL algorithm development and fair performance comparison.
  arXiv  Detail & Related papers  (2020-07-27T13:02:08Z)

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.