๐ฎ
๐ฎ
The Ethereal
FedAH: Aggregated Head for Personalized Federated Learning
December 02, 2024 ยท Entered Twilight ยท ๐ 2024 IEEE Smart World Congress (SWC)
Repo contents: .idea, LICENSE, README.md, dataset, env_cuda_latest.yaml, examples.sh, fedah.png, fedah_client.png, structure.png, system
Authors
Pengzhan Zhou, Yuepeng He, Yijun Zhai, Kaixin Gao, Chao Chen, Zhida Qin, Chong Zhang, Songtao Guo
arXiv ID
2412.01295
Category
cs.LG: Machine Learning
Cross-listed
cs.AI,
cs.DC
Citations
1
Venue
2024 IEEE Smart World Congress (SWC)
Repository
https://github.com/heyuepeng/FedAH
โญ 5
Last Checked
3 months ago
Abstract
Recently, Federated Learning (FL) has gained popularity for its privacy-preserving and collaborative learning capabilities. Personalized Federated Learning (PFL), building upon FL, aims to address the issue of statistical heterogeneity and achieve personalization. Personalized-head-based PFL is a common and effective PFL method that splits the model into a feature extractor and a head, where the feature extractor is collaboratively trained and shared, while the head is locally trained and not shared. However, retaining the head locally, although achieving personalization, prevents the model from learning global knowledge in the head, thus affecting the performance of the personalized model. To solve this problem, we propose a novel PFL method called Federated Learning with Aggregated Head (FedAH), which initializes the head with an Aggregated Head at each iteration. The key feature of FedAH is to perform element-level aggregation between the local model head and the global model head to introduce global information from the global model head. To evaluate the effectiveness of FedAH, we conduct extensive experiments on five benchmark datasets in the fields of computer vision and natural language processing. FedAH outperforms ten state-of-the-art FL methods in terms of test accuracy by 2.87%. Additionally, FedAH maintains its advantage even in scenarios where some clients drop out unexpectedly. Our code is open-accessed at https://github.com/heyuepeng/FedAH.
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