Graph Star Net for Generalized Multi-Task Learning

21 Jun 2019 Lu Haonan Seth H. Huang Tian Ye Guo Xiuyan

In this work, we present graph star net (GraphStar), a novel and unified graph neural net architecture which utilizes message-passing relay and attention mechanism for multiple prediction tasks - node classification, graph classification and link prediction. GraphStar addresses many earlier challenges facing graph neural nets and achieves non-local representation without increasing the model depth or bearing heavy computational costs... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
BENCHMARK
Text Classification 20NEWS GraphStar Accuracy 86.9 # 6
Node Classification Citeseer GraphStar Accuracy 71.0 # 37
Link Prediction Citeseer (biased evaluation) GraphStar (double weight on positive examples) AUC 97.47 # 1
AP 97.93 # 1
Accuracy 97.7 # 1
Node Classification Cora GraphStar Accuracy 82.1% # 37
Link Prediction Cora (biased evaluation) GraphStar (double weight on positive examples) AUC 95.65 # 1
AP 96.15 # 1
Accuracy 95.9 # 1
Graph Classification D&D GraphStar Accuracy 79.60% # 13
Graph Classification ENZYMES GraphStar Accuracy 67.1% # 8
Sentiment Analysis IMDb GraphStar Accuracy 96.0 # 4
Sentiment Analysis MR GraphStar Accuracy 76.6 # 12
Graph Classification MUTAG GraphStar Accuracy 91.2% # 7
Text Classification Ohsumed GraphStar Accuracy 64.2 # 6
Node Classification PPI GraphStar F1 99.4 # 6
Graph Classification PROTEINS GraphStar Accuracy 77.90% # 12
Node Classification Pubmed GraphStar Accuracy 77.2% # 41
Link Prediction Pubmed (biased evaluation) GraphStar (double weight on positive examples) AUC 97.67 # 1
AP 98.64 # 1
Accuracy 98.16 # 1
Text Classification R52 GraphStar Accuracy 95.00 # 1
Text Classification R8 GraphStar Accuracy 97.4 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet