Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
Geometric deep learning: Going beyond euclidean data,
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
k-MIP attention enables linear-complexity graph transformers that approximate full attention arbitrarily closely and bounds GraphGPS expressivity via S-SEG-WL.
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
Defines a macroscopic Kähler metric linking geometric thermodynamics to the Fisher matrix and computes exact partition functions on CV manifolds with an extended Souriau framework using Casimir functions.
REViT introduces a discrete roto-reflection equivariant convolutional vision transformer claimed to outperform prior equivariant networks on image classification.
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
Heterogeneous Graph Attention Networks model intra-domain and inter-domain sensor relationships for short-term state forecasting in multi-domain power systems, outperforming baselines by 35.5% NRMSE on a hydroelectric case study.
citing papers explorer
-
k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
k-MIP attention enables linear-complexity graph transformers that approximate full attention arbitrarily closely and bounds GraphGPS expressivity via S-SEG-WL.