Anonymous Walk Embeddings

ICML 2018 Sergey IvanovEvgeny Burnaev

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Graph Classification D&D AWE Accuracy 71.51% # 5
Graph Classification IMDb-B AWE Accuracy 74.45% # 1
Graph Classification MUTAG AWE Accuracy 87.87% # 3