PyTorch Geometric
PulseAugur coverage of PyTorch Geometric — every cluster mentioning PyTorch Geometric across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
GNNs suffer temporal leakage in financial models; new benchmark released
Researchers have identified widespread temporal leakage in message-passing graph neural networks (GNNs) when applied to financial transaction data. This leakage occurs because standard training splits can expose the mod…
-
FoldPipe system streamlines molecular ML data streaming
Researchers have developed FoldPipe, a Python orchestration layer designed to improve the efficiency of training molecular machine-learning models. This system addresses challenges with retrieving large molecular graph …
-
City2Graph library enables urban analysis with Heterogeneous Graph Neural Networks
A new Python library called City2Graph has been released, designed to transform geospatial data into analysis-ready graphs for urban systems. This library facilitates the use of Heterogeneous Graph Neural Networks (HGNN…
-
Spatial Graph Learning Pipeline for Urban Function Inference Detailed
This tutorial demonstrates how to build a spatial graph learning pipeline for urban function inference. It utilizes libraries like city2graph, OSMnx, and PyTorch Geometric to process OpenStreetMap data, construct graph …
-
New GPU kernels boost GNN performance with optimized memory access
Researchers have developed new GPU kernels to optimize Graph Neural Networks (GNNs) by addressing memory access bottlenecks. These kernels are designed to reduce data movement and improve locality for three main GNN lay…
-
Morphling synthesizer boosts GNN training speed by 20X
Researchers have developed Morphling, a domain-specific code synthesizer designed to optimize the training of Graph Neural Networks (GNNs). Morphling compiles GNN specifications into portable, backend-specialized implem…