Federated recommendation scores improved by adding semantic residual ranking
Federated Semantic Residuals for Multimodal Recommendation
Information Retrieval
Summary
Recommender systems on personal devices rank items based on user interactions, but adding text and images can change these rankings in unclear ways. The authors propose a method called SERA, which keeps the original ranking and adds a separate content-based score that only changes the order when it is strong enough. This approach lets the content influence recommendations without confusing the original collaborative ranking. Experiments show SERA improves recommendation accuracy across multiple systems and datasets without needing extra personalized data.
What this means in practice
- •For mobile app developers: Enhance federated recommendation apps by adding interpretable content-based reranking that respects user privacy without complex personalized models.
- •For e-commerce platform teams: Improve product recommendations on decentralized user data by integrating semantic content scores that boost relevant items without losing collaborative filtering benefits.
Authors
Zhiwei Li, Guodong Long, Chengqi Zhang, Jing Jiang
Abstract
Federated Recommendation Systems (FedRSs) learn collaborative scores from interaction histories on device and rank items by them, so a higher score means a higher rank. Item text and images add semantic information that can reorder the list. Existing Federated Multimodal Recommenders (FedMRs) fuse this content into their models, which can obscure how content reorders the list. We therefore propose the SEmantic Residual Adapter (SERA), which keeps content out of an existing FedRS and adds semantic residual scores to its collaborative scores. Content can then lift an item above another only when its semantic residual score exceeds the other's by more than their collaborative score gap. This score grows with the item's content similarity to the user's interaction history and is capped at a residual bound. We prove that for any content, an item can enter the list only if its collaborative score is within twice this bound of the lowest one in the list. A larger bound lets content lift more items, including irrelevant ones, so the bound trades off how far content reaches against accuracy. With a validated bound, SERA improves all three FedRSs on all six datasets without adding personalized parameters. It outperforms FedMRs in most comparisons and lifts some FedRSs above centralized baselines.