From Aggregation to Selection: User-Validated Distributed Social Recommendation
Jingyuan Huang, Dan Luo, Zihe Ye, Weixin Chen, Minghao Guo, Yongfeng Zhang
TL;DR
DeSocial confronts the challenge of distributed social recommendation by replacing opaque aggregation with user-driven algorithm selection and majority consensus among validators. It formulates recommendation as a graph link prediction task and introduces Acc@K to measure consensus-driven correctness, reporting improvements across four real datasets. The approach demonstrates that personalized model selection and multi-validator voting yield higher decision correctness and robustness than single-point or aggregate baselines, while also revealing a practical less-is-more principle in validator composition. The work highlights the potential of user-validated distributed recommendations for privacy-preserving, transparent, and scalable social graph inference with broader applicability to decentralized systems.
Abstract
Social recommender systems facilitate social connections by identifying potential friends for users. Each user maintains a local social network centered around themselves, resulting in a naturally distributed social structure. Recent research on distributed modeling for social recommender systems has gained increasing attention, as it naturally aligns with the user-centric structure of user interactions. Current distributed social recommender systems rely on automatically combining predictions from multiple models, often overlooking the user's active role in validating whether suggested connections are appropriate. Moreover, recommendation decisions are validated by individual users rather than derived from a single global ordering of candidates. As a result, standard ranking-based evaluation metrics make it difficult to evaluate whether a user-confirmed recommendation decision is actually correct. To address these limitations, we propose DeSocial, a distributed social recommendation framework with user-validation. DeSocial enables users to select recommendation algorithms to validate their potential connections, and the verification is processed through majority consensus among multiple independent user validators. To evaluate the distributed recommender system with user validator, we formulate this setting as a link prediction and verification task and introduce Acc@K, a consensus-based evaluation metric that measures whether user-approved recommendations are correct. Experiments on 4 real-world social networks shows that DeSocial improves decision correctness and robustness compared to single-point and distributed baselines. These findings highlight the potential of user-validated distributed recommender systems as a practical approach to social recommendation, with broader applicability to distributed and decentralized recommendations. Code: https://github.com/agiresearch/DeSocial.