Summary of Exploiting Label Skewness For Spiking Neural Networks in Federated Learning, by Di Yu et al.
Exploiting Label Skewness for Spiking Neural Networks in Federated Learning
by Di Yu, Xin Du, Linshan Jiang, Huijing Zhang, Shunwen Bai, Shuiguang Deng
First submitted to arxiv on: 23 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 The proposed framework, FedLEC, addresses data privacy concerns in deploying deep spiking neural networks (SNNs) on edge devices by incorporating intra-client label weight calibration and inter-client knowledge distillation. This novel approach balances learning intensity across local labels and mitigates local SNN model bias caused by label absence. FedLEC is compared to eight state-of-the-art federated learning algorithms, achieving an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FedLEC is a new way to train deep spiking neural networks (SNNs) on edge devices without sharing data. This is important because these devices are connected to lots of different things and collect a lot of data, but we don’t want that data shared publicly. The problem with current methods is that they can be affected by the quality of the data each device has. To fix this, FedLEC uses two techniques: one to make sure each device is learning at the right pace, and another to help devices learn from each other. This results in better SNN models being trained on all the devices. |
Keywords
» Artificial intelligence » Federated learning » Knowledge distillation
