Graph Neural Networks (GNNs)
PulseAugur coverage of Graph Neural Networks (GNNs) — every cluster mentioning Graph Neural Networks (GNNs) across labs, papers, and developer communities, ranked by signal.
-
New ADAPT model uses Transformer for long-range atomic interactions
Researchers have developed ADAPT, a new machine learning force field that bypasses graph neural networks for modeling atomic interactions. This approach directly uses atomic coordinates and a Transformer encoder to capt…
-
New framework tests GNNs against calibration attacks
Researchers have developed a new framework called the Unified Graph Calibration Attack (UGCA) to test the robustness of Graph Neural Networks (GNNs) against adversarial perturbations. This framework addresses challenges…
-
New LCC classifier boosts GNN performance on heterophilous graphs
Researchers have developed a new classifier called Label Context Classifier (LCC) to improve node classification in heterophilous graphs. Current Graph Neural Networks (GNNs) struggle with these graphs where nodes with …
-
New TAGR framework boosts GNN robustness with graph repair
Researchers have introduced Topology-Aware Gaussian Repair (TAGR), a novel framework designed to enhance the robustness of Graph Neural Networks (GNNs). TAGR addresses common issues in real-world graph data, such as noi…