Drift-Aware Federated Learning: A Causal Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915194253344768 |
|---|---|
| author | Fang, Yunjie Wu, Sheng Yang, Tao Wu, Xiaofeng Hu, Bo |
| author_facet | Fang, Yunjie Wu, Sheng Yang, Tao Wu, Xiaofeng Hu, Bo |
| contents | Federated learning (FL) facilitates collaborative model training among multiple clients while preserving data privacy, often resulting in enhanced performance compared to models trained by individual clients. However, factors such as communication frequency and data distribution can contribute to feature drift, hindering the attainment of optimal training performance. This paper examine the relationship between model update drift and global as well as local optimizer from causal perspective. The influence of the global optimizer on feature drift primarily arises from the participation frequency of certain clients in server updates, whereas the effect of the local optimizer is typically associated with imbalanced data distributions.To mitigate this drift, we propose a novel framework termed Causal drift-Aware Federated lEarning (CAFE). CAFE exploits the causal relationship between feature-invariant components and classification outcomes to independently calibrate local client sample features and classifiers during the training phase. In the inference phase, it eliminated the drifts in the global model that favor frequently communicating clients.Experimental results demonstrate that CAFE's integration of feature calibration, parameter calibration, and historical information effectively reduces both drift towards majority classes and tendencies toward frequently communicating nodes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09116 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Drift-Aware Federated Learning: A Causal Perspective Fang, Yunjie Wu, Sheng Yang, Tao Wu, Xiaofeng Hu, Bo Machine Learning Distributed, Parallel, and Cluster Computing Federated learning (FL) facilitates collaborative model training among multiple clients while preserving data privacy, often resulting in enhanced performance compared to models trained by individual clients. However, factors such as communication frequency and data distribution can contribute to feature drift, hindering the attainment of optimal training performance. This paper examine the relationship between model update drift and global as well as local optimizer from causal perspective. The influence of the global optimizer on feature drift primarily arises from the participation frequency of certain clients in server updates, whereas the effect of the local optimizer is typically associated with imbalanced data distributions.To mitigate this drift, we propose a novel framework termed Causal drift-Aware Federated lEarning (CAFE). CAFE exploits the causal relationship between feature-invariant components and classification outcomes to independently calibrate local client sample features and classifiers during the training phase. In the inference phase, it eliminated the drifts in the global model that favor frequently communicating clients.Experimental results demonstrate that CAFE's integration of feature calibration, parameter calibration, and historical information effectively reduces both drift towards majority classes and tendencies toward frequently communicating nodes. |
| title | Drift-Aware Federated Learning: A Causal Perspective |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2503.09116 |