Decoupling feature propagation from the design of graph auto-encoders

by   Paul Scherer, et al.

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.


page 1

page 2

page 3

page 4


Effective Decoding in Graph Auto-Encoder using Triadic Closure

The (variational) graph auto-encoder and its variants have been popularl...

HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption

Self-supervised auto-encoders have emerged as a successful framework for...

Exploring Variational Graph Auto-Encoders for Extract Class Refactoring Recommendation

The code smell is a sign of design and development flaws in a software s...

Barlow Graph Auto-Encoder for Unsupervised Network Embedding

Network embedding has emerged as a promising research field for network ...

Implicit Graphon Neural Representation

Graphons are general and powerful models for generating graphs of varyin...

How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation

We propose to exploit reconstruction as a layer-local training signal f...

Please sign up or login with your details

Forgot password? Click here to reset