TopicVAE: Topic-aware Disentanglement Representation Learning for Enhanced Recommendation

1 code implementation • ACM MM 2022 • Zhiqiang Guo, GuoHui Li, Jianjun Li, Huaicong Chen

However, most existing methods considering content information are not well-designed to disentangle user preference features due to neglecting the diversity of user preference on different semantic topics of items, resulting in sub-optimal performance and low interpretability.

Disentanglement Recommendation Systems