Learning to Make Predictions on Graphs with Autoencoders

23 Feb 2018Phi Vu Tran

We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link prediction and node classification... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification Citeseer alpha-LoNGAE Accuracy 71.60% # 24
Node Classification Cora alpha-LoNGAE Accuracy 78.30% # 36
Node Classification Pubmed alpha-LoNGAE Accuracy 79.40% # 24

Methods used in the Paper