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 interaction 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, a novel mechanism is designed to select the beneficial feature interactions and formulate them as edges between features. Then our 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 has demonstrated the rationality and effectiveness of our proposed approach.

本论文提出了一种基于图形结构和 GNN 特征汇聚策略相结合的 Graph Factorization Machine 方法，可以在处理高维度稀疏数据时有效地建模任意高阶特征交互，并具有优异的预测准确性。

GraphFM：用于特征交互建模的图形因子分解机