Abstract
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 andMF 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.
Keywords
AutoencoderOverfittingComputer scienceMatrix decompositionRegularization (linguistics)Artificial intelligenceDropout (neural networks)Machine learningSparse matrixDense graphLink (geometry)GraphPattern recognition (psychology)Artificial neural networkTheoretical computer science
Related Publications
Partitioning Sparse Matrices with Eigenvectors of Graphs
The problem of computing a small vertex separator in a graph arises in the context of computing a good ordering for the parallel factorization of sparse, symmetric matrices. An ...
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly...
A survey on Image Data Augmentation for Deep Learning
Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...
Fractional Max-Pooling
Convolutional networks almost always incorporate some form of spatial pooling, and very often it is alpha times alpha max-pooling with alpha=2. Max-pooling act on the hidden lay...
Publication Info
- Year
- 2015
- Type
- preprint
- Pages
- 451-459
- Citations
- 33
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
33
OpenAlex
Cite This
Shuangfei Zhai,
Zhongfei Zhang
(2015).
Dropout Training of Matrix Factorization and Autoencoder for Link Prediction in Sparse Graphs.
, 451-459.
https://doi.org/10.1137/1.9781611974010.51
Identifiers
- DOI
- 10.1137/1.9781611974010.51