Federated Learning with Position-Aware Neurons
Abstract
Federated Learning (FL) fuses collaborative models from local nodes without centralizing users' data. The permutation invariance property of neural networks and the non-i.i.d. data across clients make the locally updated parameters imprecisely aligned, disabling the coordinate-based parameter averaging. Traditional neurons do not explicitly consider position information. Hence, we propose Position-Aware Neurons (PANs) as an alternative, fusing position-related values (i.e., position encodings) into neuron outputs. PANs couple themselves to their positions and minimize the possibility of dislocation, even updating on heterogeneous data. We turn on/off PANs to disable/enable the permutation invariance property of neural networks. PANs are tightly coupled with positions when applied to FL, making parameters across clients pre-aligned and facilitating coordinate-based parameter averaging. PANs are algorithm-agnostic and could universally improve existing FL algorithms. Furthermore, "FL with PANs" is simple to implement and computationally friendly.
Cite
@article{arxiv.2203.14666,
title = {Federated Learning with Position-Aware Neurons},
author = {Xin-Chun Li and Yi-Chu Xu and Shaoming Song and Bingshuai Li and Yinchuan Li and Yunfeng Shao and De-Chuan Zhan},
journal= {arXiv preprint arXiv:2203.14666},
year = {2022}
}
Comments
Accepted/to be published on CVPR 2022