From Aggregation to Selection: User-Validated Distributed Social Recommendation

Jingyuan Huang, Zihe Ye

Abstract:

Social recommender systems facilitate social connections by identi-
fying potential friends for users. Each user maintains a local social
network centered around themselves, resulting in a naturally dis-
tributed 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 inter-
actions. 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 rec-
ommendation framework with user-validation. DeSocial enables
users to select recommendation algorithms to validate their poten-
tial connections, and the verification is processed through majority
consensus among multiple independent user validators. To evalu-
ate 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 four real-world social networks demonstrate 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.
Our code is available at: https://github.com/agiresearch/DeSocial.