GCN-Int: A Click-Through Rate Prediction Model Based on Graph Convolutional Network Interaction

Abstract

Recommendation system has been paid growing attention in the academia community and industry community because it can solve the problem of information overload. Among a variety of methods, the click-through rate prediction model plays an important role in predicting user's attention to a specific item. To predict click-through rate, high-dimensional and sparse features are usually adopted, and the accuracy of the prediction result depends on the combination of high-order features to a great extent. Therefore, many methods have been proposed to find the low-dimensional representation from sparse high-dimensional original features, and the meaningful way of feature combination has also been mined to improve the accuracy of the model. However, the click-through rate prediction models generally have two problems. One is that they can't extract the feature interaction of non-Euclidean features very well. Another one is that it is hard to explain the inward meaning of feature interaction. In this paper, a GCN-int model based on the interaction of Graph Convolutional Network is proposed to solve the above problems. The proposed model simplifies the complex interaction among multiple features, gets a better representation of the interaction between high-order features, and improves the interpretability of feature interaction. The experimental results on the public movie recommendation dataset and our own IPTV movie recommendation dataset show that the proposed GCN-int model gets higher accuracy and efficiency compared with the state-of-the-art models.

Explicit Feature Interaction-Aware Graph Neural Network

“…In recent years, several methods have been proposed for learning feature interactions through GNNs [22], [23], [25], [42]. These methods designate features as nodes and employ GNNs to learn edge weights within the feature graph.…”

Click-Through Rate Prediction Algorithm Based on Modeling of Implicit High-Order Feature Importance

“…Although many studies have been sufficient for user and item feature mining, they have not fully considered the user or item feature combinations or combination optimization. Based on this, a large number of rese archers have proposed CTR prediction algorithms based on feature combinations [7,[17][18][19][20][21][22]. For example, Liu et al [17] proposed a GCN-int model based on the interaction of Graph Convolutional Network to mine meaningful feature combinations.…”

“…Based on this, a large number of rese archers have proposed CTR prediction algorithms based on feature combinations [7,[17][18][19][20][21][22]. For example, Liu et al [17] proposed a GCN-int model based on the interaction of Graph Convolutional Network to mine meaningful feature combinations. Bian et al [18] propose a Co-Action Network (CAN) to approximate the explicit pairwise feature interactions without introducing too many additional parameters.…”