Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
This work provides an incremental improvement for online advertising platforms by enhancing the accuracy of CTR prediction.
This paper addresses the problem of Click-Through Rate (CTR) prediction by proposing a novel Disentangled Self-Attentive Neural Network (DESTINE) framework. DESTINE explicitly decouples unary feature importance from pairwise interaction, leading to consistent improvements over state-of-the-art baselines on two real-world benchmark datasets while maintaining computational efficiency.
Click-Through Rate (CTR) prediction, whose aim is to predict the probability of whether a user will click on an item, is an essential task for many online applications. Due to the nature of data sparsity and high dimensionality of CTR prediction, a key to making effective prediction is to model high-order feature interaction. An efficient way to do this is to perform inner product of feature embeddings with self-attentive neural networks. To better model complex feature interaction, in this paper we propose a novel DisentanglEd Self-atTentIve NEtwork (DESTINE) framework for CTR prediction that explicitly decouples the computation of unary feature importance from pairwise interaction. Specifically, the unary term models the general importance of one feature on all other features, whereas the pairwise interaction term contributes to learning the pure impact for each feature pair. We conduct extensive experiments using two real-world benchmark datasets. The results show that DESTINE not only maintains computational efficiency but achieves consistent improvements over state-of-the-art baselines.