{"repo":"6lyc/FedCEO_Collaborate-with-Each-Other","free":true,"listed":false,"github":"https://github.com/6lyc/FedCEO_Collaborate-with-Each-Other","clone":"git clone https://github.com/6lyc/FedCEO_Collaborate-with-Each-Other.git","description":"[ICML 2025] The Official implementation of our paper \"Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off\"","language":"Python","stars":23,"topics":["ai-safety","differential-privacy","federated-learning","icml","privacy","privacy-protection","python","security","utility","tradeoff"],"license":null,"category":"security-tools","readme_excerpt":"FedCEO: \"Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off\" (ICML 2025) 📣 17/12/25: Honored to have our work featured by PaperWeekly [博客] and Data Science Collective [Blog]！ 📣 06/09/25: Check out the intro to our paper on Twitter! Likes and Reposts are welcome! 📣 02/08/25: Update the Slide and Video in ICML 2025! 📣 01/05/25: This paper has been accepted to ICML 2025 ! The official implementation of our paper: Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off ( FedCEO ) [ArXiv] [OpenReview)] [Slide&Video] [X] [中文博客] [Blog] Abstract To defend against privacy leakage of user data, differential privacy is widely used in federated learning, but it is not free. The addition of noise randomly disrupts the semantic integrity of the model and this disturbance accumulates with increased communication rounds. In this paper, we introduce a novel federated learning framework with rigorous privacy guarantees, named FedCEO , designed to strike a trade-off between model utility and user privacy by letting clients \" Collaborate with Each Other \". Specifically, we perform efficient tensor low-rank proximal optimization on stacked local model parameters at the server, demonstrating its capability to flexibly truncate high-frequency components in spectral space. This capability implies that our FedCEO can effectively recover the disrupt","default_branch":null,"files":null,"tree":[],"storefront":"/r/6lyc","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/6lyc/FedCEO_Collaborate-with-Each-Other/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}