CASIA OpenIR  > 模式识别实验室
GraphFM: Graph Factorization Machines for Feature Interaction Modeling
Shu Wu1; Zekun Li; Yunyue Su1; Zeyu Cui; Xiaoyu Zhang2; Liang Wang1
发表期刊Machine Intelligence Research
2024
页码1
文章类型期刊论文(录用)
摘要

 

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 Factoriza-
tion 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 Neu-
ral 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 ratio-
nality and effectiveness of our proposed approach. The code and
data are available at https://github.com/CRIPAC-DIG/GraphCTR.

七大方向——子方向分类机器学习
国重实验室规划方向分类智能计算与学习
是否有论文关联数据集需要存交
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/57490
专题模式识别实验室
作者单位1.中国科学院自动化研究所
2.中国科学院信息工程研究所
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Shu Wu,Zekun Li,Yunyue Su,et al. GraphFM: Graph Factorization Machines for Feature Interaction Modeling[J]. Machine Intelligence Research,2024:1.
APA Shu Wu,Zekun Li,Yunyue Su,Zeyu Cui,Xiaoyu Zhang,&Liang Wang.(2024).GraphFM: Graph Factorization Machines for Feature Interaction Modeling.Machine Intelligence Research,1.
MLA Shu Wu,et al."GraphFM: Graph Factorization Machines for Feature Interaction Modeling".Machine Intelligence Research (2024):1.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
GraphFM.pdf(7938KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
录用证明GraphFM Graph Fa(272KB)其他 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Shu Wu]的文章
[Zekun Li]的文章
[Yunyue Su]的文章
百度学术
百度学术中相似的文章
[Shu Wu]的文章
[Zekun Li]的文章
[Yunyue Su]的文章
必应学术
必应学术中相似的文章
[Shu Wu]的文章
[Zekun Li]的文章
[Yunyue Su]的文章
相关权益政策
暂无数据
收藏/分享
文件名: GraphFM.pdf
格式: Adobe PDF
文件名: 录用证明GraphFM Graph Factorization Machines for Feature Interaction Modeling.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。