Flow based method improves personalized recommendation accuracy
SourceFlow: Collaborative Source Coupling for Flow-Based Recommendation
Information Retrieval
Summary
Recommendation systems try to predict what you might like by looking at your past choices, but the noise added in some methods can hide your true preferences. The authors propose SourceFlow, a technique that better guesses missing favorite items by using patterns from similar users' interactions. This method replaces some past choices with related guesses based on shared tastes, making it easier for the model to learn and recover the original preferences. Tests across multiple datasets show this approach gives more accurate recommendations than previous flow-based methods.
What this means in practice
- •For e commerce platform engineers: Enhance product recommendation quality by integrating collaborative source coupling to better predict user preferences with fewer prediction steps.
- •For video streaming service developers: Improve user content suggestions by using collaborative evidence within flow-based models to capture more personalized tastes.
Authors
Chenghao Wu, Yongqi Zhou, Jin Chen, Yifeng Zhou, Jinchang Zhu, Junwei Pan, Chao Zhou, Zhixiang Feng, Chengguo Yin, Menglin Yang
Abstract
Diffusion-based recommenders learn user preferences by denoising interaction histories, but the added noise can distort the original preference signals. Flow-based collaborative filtering (CF) instead learns a discrete path from a sampled source to the user's observed training interactions (the target history), enabling inference in a few steps. Existing flow-based CF methods sample sources using global item frequencies to reflect the sparsity and popularity of observed interactions. Each source is sampled independently of its target history, leaving the predictor without user-specific source cues for learning to reconstruct that history. We propose SourceFlow, which brings collaborative structure into the source distribution itself rather than adding further conditioning to the predictor. Like inference from observed histories, training uses collaborative evidence to predict missing interactions. Specifically, Neighborhood Coupling constructs displaced binary sources by replacing historical items with unobserved collaborative alternatives. Collaborative Consensus further refines replacement probabilities using evidence from other interactions of users who share the observed item. Stretched Restoration retains these replacements at late flow times during training, providing more opportunities to recover the original interactions. Experiments on five recommendation datasets show consistent improvements over competitive baselines, including a mean relative Recall@10 gain of 15.7% over the strongest flow-based baseline. Controlled experiments confirm that these gains depend on correctly pairing collaborative sources with their target histories, as reassigning the same source vectors across users reverses the gains. Code will be publicly released upon acceptance.