Poisoning Decentralized Collaborative Recommender System and Its Countermeasures

arXiv:2404.01177v1 Announce Type: new
Abstract: To make room for privacy and efficiency, the deployment of many recommender systems is experiencing a shift from central servers to personal devices, where the federated recommender systems (FedRecs) and decentralized collaborative recommender systems (DecRecs) are arguably the two most representative paradigms. While both leverage knowledge (e.g., gradients) sharing to facilitate learning local models, FedRecs rely on a central server to coordinate the optimization process, yet in DecRecs, the knowledge sharing directly happens between clients. …

arxiv countermeasures cs.cr cs.ir decentralized deployment devices efficiency federated knowledge personal personal devices poisoning privacy recommender systems room servers system systems