← Search

Frank Weichert

2 accepted papers

2021

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

ICML 2021spotlight

We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size with…

2018

SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels

CVPR 2018poster

We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the k…