GraphFM:Graph Factorization Machines for Feature Interaction Modelling  

作　　者：Shu Wu Zekun Li Yunyue Su Zeyu Cui Xiaoyu Zhang Liang Wang 

机构地区：[1]Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China [2]University of California,Santa Barbara 93106,USA [3]Alibaba Group,Alibaba DAMO Academy for Discovery,Adventure,Momentum and Outlook,Beijing 695571,China [4]Institute of Information Engineering,Chinese Academy of Sciences,Beijing 695571,China

出　　处：《Machine Intelligence Research》2025年第2期239-253,共15页机器智能研究(英文版)

基　　金：supported by the National Science Foundation of China(No.62141608).

摘　　要：Factorization machine(FM)is a prevalent approach to modelling pairwise(second-order)feature interactions when dealing with high-dimensional sparse data.However,on the one hand,FMs fail 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 the prediction accuracy.To solve these problems,we propose a novel approach,the graph factorization machine(GraphFM),which naturally represents features in the graph structure.In particular,we design a mechanism to select beneficial feature interactions and formulate them as edges between features.Then the proposed model,which integrates the interaction function of the FM into the feature aggregation strategy of the graph neural network(GNN),can model arbitrary-order feature interactions on graph-structured features by stacking layers.Experimental results on several real-world datasets demonstrate the rationality and effectiveness of our proposed approach.The code and data are available at https://github.com/CRIPAC-DIG/GraphCTR.

关 键 词：Feature interaction factorization machines graph neural network recommender system deep learning 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]