Search Results for author:
Found 7 papers, 4 papers with code
Synthetic Graph Generation to Benchmark Graph Learning
This shockingly small sample size (~10) allows for only limited scientific insight into the problem.
Zero-shot Transfer Learning on Heterogeneous Graphs via Knowledge Transfer Networks
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.
GraphWorld: Fake Graphs Bring Real Insights for GNNs
Using GraphWorld, a user has fine-grained control over graph generator parameters, and can benchmark arbitrary GNN models with built-in hyperparameter tuning.
Recurrent Graph Neural Networks for Rumor Detection in Online Forums
The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content.
Finding Stable Groups of Cross-Correlated Features in Two Data Sets With Common Samples
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 Clustering with Graph Neural Networks
To address these deficiencies, we introduce Deep Modularity Networks (DMoN), an unsupervised pooling method inspired by the modularity measure of clustering quality, and show how it tackles recovery of the challenging clustering structure of real-world graphs.
MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata.
