2015/12/14 by Shuangfei Zhai, Zhai, Shuangfei, Zhongfei Zhang +1 · 7 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial intelligence #Artificial neural network #Autoencoder #Bioinformatics and Genomic Networks #Complex Network Analysis Techniques #Computer science #Dense graph #Dropout (neural networks) #FOS: Computer and information sciences #Graph #Line graph #Link (geometry) #Machine Learning (cs.LG) #Machine learning #Matrix decomposition #Overfitting #Pattern recognition (psychology) #Regularization (linguistics) #Sparse matrix #Theoretical computer science #cs.LG
paper · pdf · doi:10.48550/arxiv.1512.04483
published in arXiv (Cornell University) (Cornell University) · Published in SDM 2015
arxiv created 2015/12/14 · openalex publication_date 2015/12/14 · arxiv updated 2015/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Matrix factorization (MF) and Autoencoder (AE) are among the most successful approaches of unsupervised learning. While MF based models have been extensively exploited in the graph modeling and link prediction literature, the AE family has not gained much attention. In this paper we investigate both MF and AE's application to the link prediction problem in sparse graphs. We show the connection between AE and MF from the perspective of multiview learning, and further propose MF+AE: a model training MF and AE jointly with shared parameters. We apply dropout to training both the MF and AE parts, and show that it can significantly prevent overfitting by acting as an adaptive regularization. We conduct experiments on six real world sparse graph datasets, and show that MF+AE consistently outperforms the competing methods, especially on datasets that demonstrate strong non-cohesive structures.