paper-with-me

Papers

Fast Graph Representation Learning with PyTorch Geometric

2019-03-06 · Matthias Fey, Jan Eric Lenssen

We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.

📄 PDF Abstract BibTeX arXiv:1903.02428

Code (6)

rusty1s/pytorch_geometric 공식 구현 pytorch
NMADALI97/French-web-domain-classification pytorch
leojklarner/gauche pytorch
long-9621/splinecnn pytorch
luxtu/OCTA-graph pytorch
ncfrey/litmatter pytorch

Tasks

GPUGraph ClassificationGraph Representation LearningNode ClassificationRelational ReasoningRepresentation Learning

Similar Papers 제목 키워드 기반

Tiered Graph Autoencoders with PyTorch Geometric for Molecular Graphs

2019-08-22 · Daniel T. Chang

Tiered latent representations and latent spaces for molecular graphs provide a simple but effective way to explicitly represent and utilize groups (e.g., functional groups), which consist of the atom (node) tier, the gro…

Transfer Learning

PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network

2023-11-28 · Xiyuan Wang, Muhan Zhang

We introduce PyTorch Geometric High Order (PyGHO), a library for High Order Graph Neural Networks (HOGNNs) that extends PyTorch Geometric (PyG). Unlike ordinary Message Passing Neural Networks (MPNNs) that exchange messa…

Graph Neural Network

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

2021-06-10 · Matthias Fey, Jan E. Lenssen, Frank Weichert, Jure Leskovec

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 iteration…

GPU

PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs

2022-02-22 · Yixuan He, Xitong Zhang, JunJie Huang, Benedek Rozemberczki 외

Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many networks are signed or directed, or bo…

Time SeriesTime Series Analysis

Neurally boosted supervised spectral clustering

2021-09-29 · Ali Parviz, Ioannis Koutis

Network embedding methods compute geometric representations of graphs that render various prediction problems amenable to machine learning techniques. Spectral network embeddings are based on the computation of eigenve…

ClusteringNetwork EmbeddingNode Classification