Accurate Learning of Graph Representations with Graph Multiset Pooling

Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks. Yet, obtaining an accurate representation for a graph further requires a pooling function that maps a set of node representations into a compact form... (read more)

PDF Abstract ICLR 2021 PDF ICLR 2021 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification BBBP GMT ROC-AUC 68.31 # 1
Graph Classification COLLAB GMT Accuracy 80.74% # 8
Graph Classification D&D GMT Accuracy 78.72% # 17
Graph Classification HIV GMT ROC-AUC 77.56 # 1
Graph Classification HIV dataset GMT ROC-AUC 77.56 # 1
Graph Classification IMDb-B GMT Accuracy 73.48% # 15
Graph Classification IMDb-M GMT Accuracy 50.66% # 13
Graph Classification MUTAG GMT Accuracy 83.44% # 47
Graph Classification ogbg-molhiv GMT ROC-AUC 77.6 # 1
Graph Classification PROTEINS GMT Accuracy 75.09% # 43
Graph Classification Tox21 GMT ROC-AUC 77.3 # 1
Graph Classification ToxCast GMT ROC-AUC 65.44 # 1

Methods used in the Paper


METHOD TYPE
Label Smoothing
Regularization
Residual Connection
Skip Connections
Dropout
Regularization
Dense Connections
Feedforward Networks
Scaled Dot-Product Attention
Attention Mechanisms
Layer Normalization
Normalization
Softmax
Output Functions
Adam
Stochastic Optimization
Multi-Head Attention
Attention Modules
BPE
Subword Segmentation
Transformer
Transformers