๐ฎ
๐ฎ
The Ethereal
Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping
May 29, 2024 ยท Entered Twilight ยท ๐ arXiv.org
Repo contents: FedMR.py, README.md, data, dataset.py, load_data.py, log, models.py, new_resnet.py, partition_data.py, resnet.py, resnetcifar.py, utils.py
Authors
Ziqing Fan, Jiangchao Yao, Ruipeng Zhang, Lingjuan Lyu, Ya Zhang, Yanfeng Wang
arXiv ID
2405.18983
Category
cs.LG: Machine Learning
Cross-listed
cs.DC
Citations
5
Venue
arXiv.org
Repository
https://github.com/MediaBrain-SJTU/FedMR.git
โญ 3
Last Checked
3 months ago
Abstract
Statistical heterogeneity severely limits the performance of federated learning (FL), motivating several explorations e.g., FedProx, MOON and FedDyn, to alleviate this problem. Despite effectiveness, their considered scenario generally requires samples from almost all classes during the local training of each client, although some covariate shifts may exist among clients. In fact, the natural case of partially class-disjoint data (PCDD), where each client contributes a few classes (instead of all classes) of samples, is practical yet underexplored. Specifically, the unique collapse and invasion characteristics of PCDD can induce the biased optimization direction in local training, which prevents the efficiency of federated learning. To address this dilemma, we propose a manifold reshaping approach called FedMR to calibrate the feature space of local training. Our FedMR adds two interplaying losses to the vanilla federated learning: one is intra-class loss to decorrelate feature dimensions for anti-collapse; and the other one is inter-class loss to guarantee the proper margin among categories in the feature expansion. We conduct extensive experiments on a range of datasets to demonstrate that our FedMR achieves much higher accuracy and better communication efficiency. Source code is available at: https://github.com/MediaBrain-SJTU/FedMR.git.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
๐ฎ
๐ฎ
The Ethereal
Continuous control with deep reinforcement learning
๐
๐
Old Age
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
๐
๐
Old Age
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
๐
๐
Old Age
SGDR: Stochastic Gradient Descent with Warm Restarts
๐ฎ
๐ฎ
The Ethereal