A surge of interest in Graph Convolutional Networks (GCN) has produced thousands of GCN variants, with hundreds introduced every year.
1 code implementation • 7 Jul 2022 • Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Neslihan Bulut, Jonathan Halcrow, Filipe Miguel Gonçalves de Almeida, Silvio Lattanzi, André Linhares, Brandon Mayer, Vahab Mirrokni, John Palowitch, Mihir Paradkar, Jennifer She, Anton Tsitsulin, Kevin Villela, Lisa Wang, David Wong, Bryan Perozzi
TensorFlow GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
This shockingly small sample size (~10) allows for only limited scientific insight into the problem.
We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG.
Using GraphWorld, a user has fine-grained control over graph generator parameters, and can benchmark arbitrary GNN models with built-in hyperparameter tuning.
The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content.
Given two data types, a bimodule is a pair $(A, B)$ of feature sets from the two types such that the aggregate cross-correlation between the features in $A$ and those in $B$ is large.
Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction.
In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata.