• DGL

  • Referenced in 11 articles [sw33907]
  • distills the computational patterns of GNNs into a few generalized sparse tensor operations suitable...
  • GNNExplainer

  • Referenced in 3 articles [sw37864]
  • Graph Neural Networks. Graph Neural Networks (GNNs) are a powerful tool for machine learning ... complex models, and explaining predictions made by GNNs remains unsolved. Here we propose GNNExplainer ... giving insights into errors of faulty GNNs...
  • Eigen-GNN

  • Referenced in 2 articles [sw38084]
  • Graph Structure Preserving Plug-in for GNNs. Graph Neural Networks (GNNs) are emerging machine learning ... models on graphs. Although sufficiently deep GNNs are shown theoretically capable of fully preserving graph ... empirically and analytically that the existing shallow GNNs cannot preserve graph structures well. To overcome ... general plug-in module to boost GNNs ability in preserving graph structures. Specifically, we integrate...
  • PyG

  • Referenced in 4 articles [sw41050]
  • easily write and train Graph Neural Networks (GNNs) for a wide range of applications related...
  • PairNorm

  • Referenced in 2 articles [sw38087]
  • PairNorm: Tackling Oversmoothing in GNNs. The performance of graph neural nets (GNNs) is known ... problem setting that benefits from deeper GNNs. Code is available at https://github.com/LingxiaoShawn/PairNorm...
  • XGNN

  • Referenced in 1 article [sw37866]
  • Graph Neural Networks. Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor ... promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes ... novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach ... level insights and generic understanding of how GNNs work. In particular, we propose to explain...
  • FedGraphNN

  • Referenced in 1 article [sw41837]
  • rapidly growing thanks to the capacity of GNNs in learning distributed representations from graph-structured ... suitable platform for the FL of GNNs. To this end, we introduce FedGraphNN, an open ... system that can facilitate research on federated GNNs. FedGraphNN is built on a unified formulation ... exposing significant challenges in graph FL: federated GNNs perform worse in most datasets with...
  • MIMOSA

  • Referenced in 1 article [sw41883]
  • pretrains two property agnostic graph neural networks (GNNs) for molecule topology and substructure-type prediction ... ring. For each iteration, MIMOSA uses the GNNs’ prediction and employs three basic substructure operations...
  • AliGraph

  • Referenced in 1 article [sw38083]
  • efficiently support not only existing popular GNNs but also a series of in-house developed...
  • DGL-LifeSci

  • Referenced in 1 article [sw39641]
  • Graphs in Life Science. Graph neural networks (GNNs) constitute a class of deep learning methods...
  • GraphSAGE

  • Referenced in 4 articles [sw33908]
  • GraphSAGE is a framework for inductive representation learning...
  • DropEdge

  • Referenced in 3 articles [sw37753]
  • DropEdge: Towards Deep Graph Convolutional Networks on Node...