矩阵分解
计算机科学
文字2vec
页面排名
因式分解
嵌入
理论计算机科学
随机游动
图嵌入
链接(几何体)
秩(图论)
图形
算法
人工智能
数学
组合数学
特征向量
物理
统计
量子力学
计算机网络
标识
DOI:10.1016/j.patcog.2022.108977
摘要
Learning good quality neural graph embeddings has long been achieved by minimizing the point-wise mutual information (PMI) for co-occurring nodes in simulated random walks. This design choice has been mostly popularized by the direct application of the highly-successful word embedding algorithm word2vec to predicting the formation of new links in social, co-citation, and biological networks. However, such a skeuomorphic design of graph embedding methods entails a truncation of information coming from pairs of nodes with low PMI. To circumvent this issue, we propose an improved approach to learning low-rank factorization embeddings that incorporate information from such unlikely pairs of nodes and show that it can improve the link prediction performance of baseline methods from 1.2% to 24.2%. Based on our results and observations we outline further steps that could improve the design of next graph embedding algorithms that are based on matrix factorization.
科研通智能强力驱动
Strongly Powered by AbleSci AI