Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation
This work addresses the need for better preference understanding in recommender systems, offering a novel causal approach that is incremental over existing disentanglement methods.
The paper tackles the problem of complex and entangled user interaction data in recommendation systems by introducing the Causal Disentangled Variational Auto-Encoder (CaD-VAE), which learns causal disentangled representations to improve robustness, interpretability, and controllability, and it outperforms existing methods.
Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to uncover their underlying representation can improve the robustness, interpretability, and controllability of recommendation models. This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems. The CaD-VAE method considers the causal relationships between semantically related factors in real-world recommendation scenarios, rather than enforcing independence as in existing disentanglement methods. The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors. The results demonstrate that CaD-VAE outperforms existing methods, offering a promising solution for disentangling complex user behavior data in recommendation systems.