A new open-source library standardizes 20 hierarchical graph pooling operations under one SRCL interface with uniform outputs and batch handling for PyTorch Geometric.
A new model for learning in graph domains
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3representative citing papers
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.
citing papers explorer
-
Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks
A new open-source library standardizes 20 hierarchical graph pooling operations under one SRCL interface with uniform outputs and batch handling for PyTorch Geometric.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
xAI-Drop: Don't Use What You Cannot Explain
xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.