Causal Structure Representation Learning of Confounders in Latent Space for Recommendation

TL;DR

This paper introduces CSC, a novel VAE-based model that disentangles confounders from user preferences in latent space using causal graphs, improving recommendation accuracy and interpretability.

Contribution

It proposes a causal graph-based approach to model confounders in latent space, with theoretical identifiability and practical advantages demonstrated on multiple datasets.

Findings

Outperforms existing models on synthetic and real datasets

Learned causal confounder representations are controllable

The causal graph structure is theoretically identifiable

Abstract

Inferring user preferences from the historical feedback of users is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent to the real user preferences without additional noise, which simplifies the problem modeling. However, there are various confounders during user-item interactions, such as weather and even the recommendation system itself. Therefore, neglecting the influence of confounders will result in inaccurate user preferences and suboptimal performance of the model. Furthermore, the unobservability of confounders poses a challenge in further addressing the problem. To address these issues, we refine the problem and propose a more rational solution. Specifically, we consider the influence of confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels. By cleverly combining local and global causal graphs, we capture the user-specificity of confounders on user preferences. We theoretically demonstrate the identifiability of the obtained causal graph. Finally, we propose our model based on Variational Autoencoders, named Causal Structure representation learning of Confounders in latent space (CSC). We conducted extensive experiments on one synthetic dataset and five real-world datasets, demonstrating the superiority of our model. Furthermore, we demonstrate that the learned causal representations of confounders are controllable, potentially offering users fine-grained control over the objectives of their recommendation lists with the learned causal graphs.