Master's in Mathematics student at Jilin University
Jilin University
No. 2699 Qianjin Street
Changchun, Jilin Province China, 130012
Hello, I’m Yaming! I am a master’s student in the School of Artificial Intelligence of Jilin University, interested in Federated Learning, Out-of-distribution, and Continuous Learning.
Out-of-distribution generalization is challenging for non-participating clients of federated learning under distribution shifts. A proven strategy is to explore those invariant relationships between input and target variables, working equally well for non-participating clients. However, learning invariant relationships is often in an explicit manner from data, representation, and distribution, which violates the federated principles of privacy-preserving and limited communication. In this paper, we propose \textscFedIIR, which implicitly learns invariant relationships from parameter for out-of-distribution generalization, adhering to the above principles. Specifically, we utilize the prediction disagreement to quantify invariant relationships and implicitly reduce it through inter-client gradient alignment. Theoretically, we demonstrate the range of non-participating clients to which \textscFedIIR is expected to generalize and present the convergence results for \textscFedIIR in the massively distributed with limited communication. Extensive experiments show that \textscFedIIR significantly outperforms relevant baselines in terms of out-of-distribution generalization of federated learning.
@article{guo2023out,title={Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships},author={Guo, Yaming and Guo, Kai and Cao, Xiaofeng and Wu, Tieru and Chang, Yi},booktitle={International Conference on Machine Learning},year={2023},}
You can even add a little note about which of these is the best way to reach you.