MLLGNov 21, 2016

Variational Graph Auto-Encoders

arXiv:1611.07308v14315 citations
Originality Incremental advance
AI Analysis

It addresses the problem of link prediction in graph data for researchers and practitioners, with an incremental improvement by incorporating node features to enhance performance.

The paper tackled unsupervised learning on graph-structured data by introducing the variational graph auto-encoder (VGAE), which learns interpretable latent representations and achieves competitive results on link prediction tasks in citation networks.

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.

Code Implementations22 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes