此外,联邦学习框架往往还会有持续不断的新用户的参与,这些新用户往往有着大量的新数据类别,这样会进一步加剧全局模型的灾难性遗忘。为了应对这些挑战,我们提出了一种全新的全局-局部遗忘补偿 (GLFC) 模型,即同时从global和local两个角度出发,尽可能地减弱灾难性遗忘,使得联邦学习最终可训练一个全局增量模型。
[54] L. Zhang, L. Shen, L. Ding, D. Tao, and L. Duan (2022) Fine-tuning global model via data-free knowledge distillation for non-iid federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10174–10183. [55] Y. Zhao, M. Li...
client-variance-reduction (CVR) schemes被提出,但都有缺陷,比如有些没考虑异构局部更新,有些在non-iid下收敛还是慢。 最近的研究表明,基于交替方向乘子法( Alternating Direction Method of Multipliers,ADMM )的原始-对偶FL方法具有对数据和系统异质性的内在鲁棒性,如FedPD、Fed ADMM和FedDyn。 然而,分布式ADMM算法...
Federated Learning of a Mixture of Global and Local ModelsFilip HanzelyPeter Richtarik
Federated Learning Simulator (FLSim) is a flexible, standalone library written in PyTorch that simulates FL settings with a minimal, easy-to-use API. FLSim is domain-agnostic and accommodates many use cases such as computer vision and natural text. Currently FLSim supports cross-device FL, ...
Federated learning (FL) is a trending training paradigm to utilize decentralized training data. FL allows clients to update model parameters locally for several epochs, then share them to a global model for aggregation. This training paradigm with multi-local step updating before aggregation exposes ...
Obtaining the balance between information loss and training accuracy is crucial in federated learning. Nevertheless, inadequate data quality will affect training accuracy. Here, to improve the training accuracy without affecting information loss, we prop
Figure 1. High-level overview of federated learning employing the FedAvg algorithm. At first, a global model 𝐖𝑡0Wt0 is prepared by the server (step 1) and disseminated to the clients selected for the first training round 𝑡0t0 (step 2), the clients update their local model state at...
1. Federated Continual Learning with Weighted Inter-client Transfer (ICML 2021)该工作提出了一种联邦...
联邦学习、数据异质性、贝叶斯理论 L. Liu et al., "A Bayesian Federated Learning Framework With Online Laplace Approximation," in IEEE Transactions on Pattern Analysis and Machin...