GraphFM: Graph Factorization Machines for Feature Interaction Modeling
This work addresses feature interaction modeling in high-dimensional sparse data for machine learning applications, offering a novel hybrid method that is incremental in combining existing techniques.
The paper tackles the limitations of Factorization Machines (FM) in capturing higher-order feature interactions and handling noise from pairwise interactions by proposing Graph Factorization Machine (GraphFM), which uses a graph structure to select beneficial interactions and integrates FM with Graph Neural Networks, achieving improved prediction accuracy on real-world datasets.
Factorization machine (FM) is a prevalent approach to modeling pairwise (second-order) feature interactions when dealing with high-dimensional sparse data. However, on the one hand, FM fails to capture higher-order feature interactions suffering from combinatorial expansion. On the other hand, taking into account interactions between every pair of features may introduce noise and degrade prediction accuracy. To solve the problems, we propose a novel approach, Graph Factorization Machine (GraphFM), by naturally representing features in the graph structure. In particular, we design a mechanism to select the beneficial feature interactions and formulate them as edges between features. Then the proposed model, which integrates the interaction function of FM into the feature aggregation strategy of Graph Neural Network (GNN), can model arbitrary-order feature interactions on the graph-structured features by stacking layers. Experimental results on several real-world datasets have demonstrated the rationality and effectiveness of our proposed approach. The code and data are available at https://github.com/CRIPAC-DIG/GraphCTR}{https://github.com/CRIPAC-DIG/GraphCTR