Stochastic Blockmodels meet Graph Neural Networks

Authors: Nikhil Mehta, Lawrence Carin Duke, Piyush Rai

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on several benchmarks demonstrate encouraging results on link prediction while learning an interpretable latent structure that can be used for community discovery.
Researcher Affiliation Academia 1Department of Electrical and Computer Engineering, Duke University 2Department of Computer Science, IIT Kanpur.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., a URL or an explicit statement of code release) for its source code.
Open Datasets Yes We consider five real-world datasets... NIPS12: The NIPS12 coauthor network (Zhou, 2015)... Yeast: The Yeast protein interaction network (Zhou, 2015)... Cora: Cora network is a citation network... Citeseer: Citeseer is a citation network... Pubmed: A citation network...
Dataset Splits Yes For all datasets, we hold out 10% and 5% of the links as our test set and validation set, respectively, and use the validation set to fine-tune the hyperparameters.
Hardware Specification No The paper does not provide specific details about the hardware used for running its experiments.
Software Dependencies No The paper mentions using a "graph convolutional network (GCN)" and "Stochastic Gradient Variational Bayes (SGVB)" which imply certain software frameworks, but it does not specify any software components with version numbers (e.g., TensorFlow 2.x, PyTorch 1.x).
Experiment Setup Yes For all datasets, we hold out 10% and 5% of the links as our test set and validation set, respectively, and use the validation set to fine-tune the hyperparameters. ... The hyperparameter settings used for all experiments are included in the Supplementary Material.