paper-with-me

Papers

Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning

2021-09-29 · Haizhou Shi, Youcai Zhang, Zijin Shen, Siliang Tang, Yaqian Li, Yandong Guo, Yueting Zhuang

This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection. Existing works either conduct annotation-guided local training which requires frequent communication or aggregates the client models via weight averaging which has potential risks of privacy exposure. To tackle the above problems, we first identify that self-supervised contrastive local training is robust against the non-identically distributed data, which provides the feasibility of longer local training and thus reduces the communication cost. Then based on the aforementioned robustness, we propose a novel Federated representation Learning framework with Ensemble Similarity Distillation~(FLESD) that utilizes this robustness. At each round of communication, the server first gathers a fraction of the clients' inferred similarity matrices on a public dataset. Then it ensembles the similarity matrices and train the global model via similarity distillation. We verify the effectiveness of FLESD by a series of empirical experiments and show that, despite stricter constraints, it achieves comparable results under multiple settings on multiple datasets.

📄 PDF Abstract BibTeX arXiv:2109.14611

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningFederated LearningPrivacy PreservingRepresentation Learning

Similar Papers 제목 키워드 기반

Practical Vertical Federated Learning with Unsupervised Representation Learning

2022-08-13 · Zhaomin Wu, Qinbin Li, Bingsheng He

As societal concerns on data privacy recently increase, we have witnessed data silos among multiple parties in various applications. Federated learning emerges as a new learning paradigm that enables multiple parties to …

Federated LearningPrivacy PreservingRepresentation LearningVertical Federated Learning

Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks

2026-05-25 · Zhishuai Guo, Wenhan Wu, Chen Chen, Lei Zhang 외 arxiv

Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing fede…

FedDCL: a federated data collaboration learning as a hybrid-type privacy-preserving framework based on federated learning and data collaboration

2024-09-27 · Akira Imakura, Tetsuya Sakurai

Recently, federated learning has attracted much attention as a privacy-preserving integrated analysis that enables integrated analysis of data held by multiple institutions without sharing raw data. On the other hand, fe…

Federated LearningPrivacy Preserving

Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation

2021-09-12 · EMNLP 2021 11 · Jingwei Yi, Fangzhao Wu, Chuhan Wu, Ruixuan Liu 외

News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, which may lead to privacy concerns and ha…

Federated LearningNews RecommendationPrivacy Preserving

Privacy-preserving Decentralized Aggregation for Federated Learning

2020-12-13 · Beomyeol Jeon, S. M. Ferdous, Muntasir Raihan Rahman, Anwar Walid

Federated learning is a promising framework for learning over decentralized data spanning multiple regions. This approach avoids expensive central training data aggregation cost and can improve privacy because distribute…

Federated Learningimage-classificationImage ClassificationPrivacy Preserving