FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-Based Optimization
Abstract
Term rewriting plays a crucial role in software verification and compiler optimization. With dozens of highly parameterizable techniques developed to prove various system properties, automatic term rewriting tools work in an extensive parameter space. This complexity exceeds human capacity for parameter selection, motivating an investigation into automated strategy invention. In this paper, we focus on confluence of term rewrite systems, and apply AI techniques to invent strategies for automatic confluence proving. Moreover, we randomly generate a large dataset to analyze confluence for term rewrite systems. We improve the state-of-the-art automatic confluence prover CSI: When equipped with our invented strategies, it surpasses its human-designed strategies both on the augmented dataset and on the original human-created benchmark dataset ARI-COPS, proving/disproving the confluence of several term rewrite systems for which no automated proofs were known before.
Cite
Text
Ning et al. "FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-Based Optimization." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/526Markdown
[Ning et al. "FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-Based Optimization." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/ning2024ijcai-fedgcs/) doi:10.24963/ijcai.2024/526BibTeX
@inproceedings{ning2024ijcai-fedgcs,
title = {{FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-Based Optimization}},
author = {Ning, Zhiyuan and Tian, Chunlin and Xiao, Meng and Fan, Wei and Wang, Pengyang and Li, Li and Wang, Pengfei and Zhou, Yuanchun},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {4760-4768},
doi = {10.24963/ijcai.2024/526},
url = {https://mlanthology.org/ijcai/2024/ning2024ijcai-fedgcs/}
}