Orthogonal Hyper-category Guided Multi-interest Elicitation for Micro-video Matching
This addresses micro-video recommendation for users by improving matching accuracy and diversity, though it is incremental as it builds on existing multi-interest methods.
The paper tackles the problem of matching micro-videos to users by modeling multiple heterogeneous interests, proposing the OPAL model that uses orthogonal hyper-categories to guide interest elicitation and a two-stage training strategy. Results show OPAL outperforms six state-of-the-art models in recall and hit rate on two real-world datasets.
Watching micro-videos is becoming a part of public daily life. Usually, user watching behaviors are thought to be rooted in their multiple different interests. In the paper, we propose a model named OPAL for micro-video matching, which elicits a user's multiple heterogeneous interests by disentangling multiple soft and hard interest embeddings from user interactions. Moreover, OPAL employs a two-stage training strategy, in which the pre-train is to generate soft interests from historical interactions under the guidance of orthogonal hyper-categories of micro-videos and the fine-tune is to reinforce the degree of disentanglement among the interests and learn the temporal evolution of each interest of each user. We conduct extensive experiments on two real-world datasets. The results show that OPAL not only returns diversified micro-videos but also outperforms six state-of-the-art models in terms of recall and hit rate.