Optimizing Feature Interaction via Information Bottleneck for CTR Prediction

Lei Sang, Hanwei Li, Honghao Li, Yiwen Zhang, Xindong Wu

Abstract: Click-through rate (CTR) prediction plays a pivotal role in recommender systems and online advertising by estimating the probability of user engagement with recommended items or advertisements. However, existing methodologies encounter multiple challenges. First, current approaches often struggle to maintain robustness in the presence of noise. This challenge arises from the inherent complexity of real-world data, where noisy or irrelevant features can significantly impact model performance. Second, while existing models may achieve high accuracy, their inner workings are often lacking in interpretability, hindering users’ comprehension of the reasoning behind specific predictions. Third, conventional complex model architectures often suffer from the issue of excessive parameterization, which can be unacceptable when dealing with large-scale datasets, potentially leading to computational inefficiencies. In this study, we present information bottleneck deep cross network (IBNet) with the mice activation function to address these challenges. IBNet leverages the information bottleneck principle with contrastive learning to adaptively filter noise in high-order feature interactions, while mice ensure full information flow and prevents over-parameterization. Additionally, this article provides interpretability from the perspective of invariable and variable factors. Comprehensive experiments on four datasets demonstrate IBNet’s robustness, interpretability, and parameter efficiency, with mice proving beneficial across diverse deep learning CTR models.

External IDs:doi:10.1109/tcss.2025.3635214