FEDRKG: A Privacy-Preserving Federated Recommendation Framework via Knowledge Graph Enhancement

Yao, D., Liu, T., Cao, Q. and Jin, H. (2024) FEDRKG: A Privacy-Preserving Federated Recommendation Framework via Knowledge Graph Enhancement. In: Jin, H., Yu, Z., Yu, C., Zhou, X., Lu, Z. and Song, X. (eds.) Green, Pervasive, and Cloud Computing: 18th International Conference, GPC 2023, Harbin, China, September 22–24, 2023, Proceedings; Part II. Series: Lecture Notes in Computer Science (14504). Springer Singapore: Singapore, pp. 81-96. ISBN 9789819998951 (doi: 10.1007/978-981-99-9896-8_6)

Abstract

Federated Learning (FL) has emerged as a promising approach for preserving data privacy in recommendation systems by training models locally. Recently, Graph Neural Networks (GNN) have gained popularity in recommendation tasks due to their ability to capture highorder interactions between users and items. However, privacy concerns prevent the global sharing of the entire user-item graph. To address this limitation, some methods create pseudo-interacted items or users in the graph to compensate for missing information for each client. Unfortunately, these methods introduce random noise and raise privacy concerns. In this paper, we propose FedRKG, a novel federated recommendation system, where a global knowledge graph (KG) is constructed and maintained on the server using publicly available item information, enabling higher-order user-item interactions. On the client side, a relation-aware GNN model leverages diverse KG relationships. To protect local interaction items and obscure gradients, we employ pseudo-labeling and Local Differential Privacy (LDP). Extensive experiments conducted on three real-world datasets demonstrate the competitive performance of our approach compared to centralized algorithms while ensuring privacy preservation. Moreover, FedRKG achieves an average accuracy improvement of 4% compared to existing federated learning baselines.

• Item Type: Book Sections
• Additional Information: This work is supported by the National Natural Science Foundation of China under Grant No.62072204, 62032008, and the Fundamental Research Funds for the Central Universities under Grant HUST:2020kfyXJJS019. eISBN - 9789819998968, eISSN - 1611-3349
• Status: Published
• Glasgow Author(s) Enlighten ID: Cao, Dr Qi
• Authors: Yao, D., Liu, T., Cao, Q., and Jin, H.
• College/School: College of Science and Engineering > School of Computing Science
• Publisher: Springer Singapore
• ISBN: 9789819998951
• Copyright Holders: Copyright: © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024
• First Published: First published in Green, Pervasive, and Cloud Computing: 18th International Conference, GPC 2023 Harbin, China, September 22–24, 2023 Proceedings, Part II: 81-96
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Publisher