NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
Journal of Machine Learning Research , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
An additive MLP-GNN framework with pretraining on AqSolDB and fine-tuning on BigSolDB2 separates chemical and structural contributions to solubility while achieving competitive accuracy and enabling post-hoc interpretability analyses.
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.
citing papers explorer
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
-
An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility
An additive MLP-GNN framework with pretraining on AqSolDB and fine-tuning on BigSolDB2 separates chemical and structural contributions to solubility while achieving competitive accuracy and enabling post-hoc interpretability analyses.
-
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.