Tricolore: Multi-Behavior User Profiling for Enhanced Candidate Generation in Recommender Systems

Online platforms aggregate extensive user feedback across diverse behaviors, providing a rich source for enhancing user engagement. Traditional recommender systems, however, typically optimize for a single target behavior and represent user preferences with a single vector, limiting their ability to handle multiple equally important behaviors or diverse optimization objectives. This approach also struggles to capture the full spectrum of user interests, resulting in a narrow item pool during candidate generation. To address these limitations, we present Tricolore, a versatile multi-vector learning framework designed to uncover connections between various behavior types for more robust candidate generation. Tricolore's adaptive multi-task structure is customizable to specific platform needs. To manage the variability in sparsity across behavior types, we incorporate a behavior-wise multi-view fusion module that dynamically enhances learning. Additionally, a popularity-balanced strategy ensures the recommendation list balances accuracy with item popularity, fostering diversity and improving overall performance. Extensive experiments on public datasets demonstrate Tricolore's effectiveness in diverse recommendation scenarios, from short video platforms to e-commerce. Furthermore, by leveraging a shared base embedding strategy, Tricolore shows significant improvements, particularly for cold-start users. The source code is publicly available at: https://github.com/abnering/Tricolore