IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

22 Jul 2019Lin MengJiawei Zhang

Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Graph Classification BP-fMRI-97 IsoNN-fast Accuracy 62.3% # 3
Graph Classification BP-fMRI-97 IsoNN-fast F1 63.2% # 4
Graph Classification BP-fMRI-97 IsoNN Accuracy 64.9% # 1
Graph Classification BP-fMRI-97 IsoNN F1 69.7% # 1
Graph Classification HIV-DTI-77 IsoNN Accuracy 67.5% # 1
Graph Classification HIV-DTI-77 IsoNN F1 68.3% # 1
Graph Classification HIV-DTI-77 IsoNN-fast Accuracy 60.1% # 4
Graph Classification HIV-DTI-77 IsoNN-fast F1 61.9% # 3
Graph Classification HIV-fMRI-77 IsoNN Accuracy 73.4% # 1
Graph Classification HIV-fMRI-77 IsoNN F1 72.2% # 1
Graph Classification HIV-fMRI-77 IsoNN-Fast Accuracy 70.5% # 2
Graph Classification HIV-fMRI-77 IsoNN-Fast F1 69.9% # 2