Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.
Condensing graphs via one-step gradient matching
3 Pith papers cite this work, alongside 15 external citations. Polarity classification is still indexing.
3
Pith papers citing it
15
external citations · external index
verdicts
UNVERDICTED 3representative citing papers
FIT-GNN applies graph coarsening during inference to deliver orders-of-magnitude faster single-node inference and lower memory use on node and graph classification/regression tasks while keeping competitive accuracy.
An AutoML pipeline using SPECTER embeddings, meta-learning clustering, successive-halving topic modeling, and ARIMA/Prophet/LSTM forecasting is applied to abstracts to predict topic trends in wireless networks, reporting RMSE 36.76.
citing papers explorer
-
Rapid training of Hamiltonian graph networks using random features
Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.
-
FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening
FIT-GNN applies graph coarsening during inference to deliver orders-of-magnitude faster single-node inference and lower memory use on node and graph classification/regression tasks while keeping competitive accuracy.
-
Forecasting Technological Directions in Wireless Networks and Mobile Computing via AutoML Framework
An AutoML pipeline using SPECTER embeddings, meta-learning clustering, successive-halving topic modeling, and ARIMA/Prophet/LSTM forecasting is applied to abstracts to predict topic trends in wireless networks, reporting RMSE 36.76.