Recommendation Through Mixtures of Heterogeneous Item Relationships
This addresses the nuanced need for personalized recommendations that integrate multiple signals, such as user feedback and item relationships, for users of recommender systems, representing an incremental improvement over single-signal approaches.
The paper tackled the problem of combining heterogeneous item relationships in recommender systems by developing a framework that models user susceptibility to different recommendation modalities and selects the best recommendation from each, resulting in more accurate recommendations with intuitive explanations.
Recommender Systems have proliferated as general-purpose approaches to model a wide variety of consumer interaction data. Specific instances make use of signals ranging from user feedback, item relationships, geographic locality, social influence (etc.). Typically, research proceeds by showing that making use of a specific signal (within a carefully designed model) allows for higher-fidelity recommendations on a particular dataset. Of course, the real situation is more nuanced, in which a combination of many signals may be at play, or favored in different proportion by individual users. Here we seek to develop a framework that is capable of combining such heterogeneous item relationships by simultaneously modeling (a) what modality of recommendation is a user likely to be susceptible to at a particular point in time; and (b) what is the best recommendation from each modality. Our method borrows ideas from mixtures-of-experts approaches as well as knowledge graph embeddings. We find that our approach naturally yields more accurate recommendations than alternatives, while also providing intuitive `explanations' behind the recommendations it provides.