Strategies for Pre-training Graph Neural Networks

Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to this challenge is to pre-train a model on related tasks where data is abundant, and then fine-tune it on a downstream task of interest... (read more)

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Drug Discovery BACE ContextPred AUC 0.845 # 4
Drug Discovery BBBP ContextPred AUC 0.687 # 2
Drug Discovery ClinTox ContextPred AUC 0.726 # 2
Drug Discovery HIV dataset ContextPred AUC 0.799 # 4
Drug Discovery MUV ContextPred AUC 0.813 # 4
Drug Discovery SIDER ContextPred AUC 0.627 # 2
Drug Discovery Tox21 ContextPred AUC 0.781 # 7
Drug Discovery ToxCast ContextPred AUC 0.657 # 4

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