Deep sequence models develop geometric memory in embeddings that encodes novel global relationships, transforming l-fold composition tasks into 1-step navigation via a natural spectral bias connected to Node2Vec.
Graph neural networks: A review of methods and applications.AI Open, 1:57–81
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
A GNN trained on ANSYS-simulated two-story frame data predicts displacements and rotations more accurately than a standard neural network.
citing papers explorer
-
Deep sequence models tend to memorize geometrically; it is unclear why
Deep sequence models develop geometric memory in embeddings that encodes novel global relationships, transforming l-fold composition tasks into 1-step navigation via a natural spectral bias connected to Node2Vec.
-
GNN for Structural Displacement Prediction
A GNN trained on ANSYS-simulated two-story frame data predicts displacements and rotations more accurately than a standard neural network.