Subgraph Federated Learning for Local Generalization
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_ | 1866913721666764800 |
|---|---|
| author | Kim, Sungwon Lee, Yoonho Oh, Yunhak Lee, Namkyeong Yun, Sukwon Lee, Junseok Kim, Sein Yang, Carl Park, Chanyoung |
| author_facet | Kim, Sungwon Lee, Yoonho Oh, Yunhak Lee, Namkyeong Yun, Sukwon Lee, Junseok Kim, Sein Yang, Carl Park, Chanyoung |
| contents | Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising the privacy of each client. However, existing methods often overlook the mutable nature of graph data, which frequently introduces new nodes and leads to shifts in label distribution. Since they focus solely on performing well on each client's local data, they are prone to overfitting to their local distributions (i.e., local overfitting), which hinders their ability to generalize to unseen data with diverse label distributions. In contrast, our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting. Our model generates global synthetic data by condensing the reliable information from each class representation and its structural information across clients. Using these synthetic data as a training set, we alleviate the local overfitting problem by adaptively generalizing the absent knowledge within each local dataset. This enhances the generalization capabilities of local models, enabling them to handle unseen data effectively. Our model outperforms baselines in our proposed experimental settings, which are designed to measure generalization power to unseen data in practical scenarios. Our code is available at https://github.com/sung-won-kim/FedLoG |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03995 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Subgraph Federated Learning for Local Generalization Kim, Sungwon Lee, Yoonho Oh, Yunhak Lee, Namkyeong Yun, Sukwon Lee, Junseok Kim, Sein Yang, Carl Park, Chanyoung Machine Learning Artificial Intelligence Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising the privacy of each client. However, existing methods often overlook the mutable nature of graph data, which frequently introduces new nodes and leads to shifts in label distribution. Since they focus solely on performing well on each client's local data, they are prone to overfitting to their local distributions (i.e., local overfitting), which hinders their ability to generalize to unseen data with diverse label distributions. In contrast, our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting. Our model generates global synthetic data by condensing the reliable information from each class representation and its structural information across clients. Using these synthetic data as a training set, we alleviate the local overfitting problem by adaptively generalizing the absent knowledge within each local dataset. This enhances the generalization capabilities of local models, enabling them to handle unseen data effectively. Our model outperforms baselines in our proposed experimental settings, which are designed to measure generalization power to unseen data in practical scenarios. Our code is available at https://github.com/sung-won-kim/FedLoG |
| title | Subgraph Federated Learning for Local Generalization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.03995 |