1 code implementation • 4 Apr 2022 • Anton Tsitsulin, Benedek Rozemberczki, John Palowitch, Bryan Perozzi
This shockingly small sample size (~10) allows for only limited scientific insight into the problem.
no code implementations • 3 Mar 2022 • Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi
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.
1 code implementation • 28 Feb 2022 • John Palowitch, Anton Tsitsulin, Brandon Mayer, Bryan Perozzi
Using GraphWorld, a user has fine-grained control over graph generator parameters, and can benchmark arbitrary GNN models with built-in hyperparameter tuning.
1 code implementation • 8 Aug 2021 • Di Huang, Jacob Bartel, John Palowitch
The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content.
1 code implementation • 10 Sep 2020 • Miheer Dewaskar, John Palowitch, Mark He, Michael I. Love, Andrew B. Nobel
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.
no code implementations • 30 Jun 2020 • Anton Tsitsulin, John Palowitch, Bryan Perozzi, Emmanuel Müller
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.
no code implementations • 25 Sep 2019 • John Palowitch, Bryan Perozzi
In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata.