Decoupling feature propagation from the design of graph auto-encoders
arXiv:1910.08589
Abstract
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures. This decoupling enables the independent and fixed design of the auto-encoder without requiring additional GCN layers for every desired increase in the size of a node's local receptive field. Fixing the auto-encoder enables a fairer assessment on the size of a nodes receptive field in building representations. Furthermore a by-product of fixing the auto-encoder design often results in substantially smaller networks than their VGAE counterparts especially as we increase the number of feature propagations. A comparative downstream evaluation on link prediction tasks show comparable state of the art performance to similar VGAE arrangements despite considerable simplification. We also show the simple application of our methodology to more challenging representation learning scenarios such as spatio-temporal graph representation learning.
arXiv comment4 pages (considering single anonymous naming during original submission, now a few lines over 4). Originally submitted to NeurIPS 2019 Graph Representation Learning Workshop
References in corpus (8)
- Auto-Encoding Variational Bayes
- Sequence to Sequence Learning with Neural Networks
- Geometric deep learning: going beyond Euclidean data
- Graph Embedding Techniques, Applications, and Performance: A Survey
- Simplifying Graph Convolutional Networks
- Variational Graph Auto-Encoders
- The CTU Prague Relational Learning Repository
- Spatio-Temporal Deep Graph Infomax