GraphSculptor builds efficient pre-training coresets for graph self-supervised learning using combined structural and semantic diversity metrics, achieving 99.6% performance with 10% of the data.
A survey of pretraining on graphs: Taxonomy, methods, and applications.arXiv:2202.07893
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
SUPT assigns prompt features at the subgraph level to enable universal prompt tuning for any GNN pre-training strategy and outperforms fine-tuning in 42 of 45 full-shot and 41 of 45 few-shot graph experiments with average gains of 2.5% and 6.6%.
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.
citing papers explorer
-
GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning
GraphSculptor builds efficient pre-training coresets for graph self-supervised learning using combined structural and semantic diversity metrics, achieving 99.6% performance with 10% of the data.
-
Subgraph-level Universal Prompt Tuning
SUPT assigns prompt features at the subgraph level to enable universal prompt tuning for any GNN pre-training strategy and outperforms fine-tuning in 42 of 45 full-shot and 41 of 45 few-shot graph experiments with average gains of 2.5% and 6.6%.
-
Handling Feature Heterogeneity with Learnable Graph Patches
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.