Loading Now

Summary of Gradient-congruity Guided Federated Sparse Training, by Chris Xing Tian et al.


Gradient-Congruity Guided Federated Sparse Training

by Chris Xing Tian, Yibing Liu, Haoliang Li, Ray C.C. Cheung, Shiqi Wang

First submitted to arxiv on: 2 May 2024

Categories

  • Main: Machine Learning (cs.LG)
  • Secondary: Artificial Intelligence (cs.AI)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
This paper proposes a novel federated learning method called Gradient-Congruity Guided Federated Sparse Training (FedSGC) to address the challenges of high computational and communication costs, as well as poor generalization performance in resource-constrained edge devices. FedSGC integrates dynamic sparse training and gradient congruity inspection into the federated learning framework. The method identifies neurons with conflicting gradients and prunes them during training, reducing local computation and communication overheads while enhancing generalization abilities. The authors evaluate FedSGC on challenging non-i.i.d settings and show that it achieves competitive accuracy with state-of-the-art FL methods across various scenarios.
Low GrooveSquid.com (original content) Low Difficulty Summary
Federated learning is a way to train AI models on many devices at once, without sharing private data. This paper introduces a new method called FedSGC that makes this process more efficient and effective. It works by identifying which parts of the model are not useful for other devices and removing them. This reduces the amount of computing and communication needed, making it faster and cheaper to train models on edge devices.

Keywords

» Artificial intelligence  » Federated learning  » Generalization