Graphite: Iterative Generative Modeling of Graphs

Authors: Aditya Grover, Aaron Zweig, Stefano Ermon

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

Reproducibility Variable Result LLM Response
Research Type Experimental On a wide variety of synthetic and benchmark datasets, Graphite outperforms competing approaches for the tasks of density estimation, link prediction, and node classification. We evaluate Graphite on tasks involving entire graphs, nodes, and edges.
Researcher Affiliation Academia 1Department of Computer Science, Stanford University, USA.
Pseudocode No The paper describes algorithmic steps and equations, but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described, such as a specific repository link or an explicit code release statement.
Open Datasets Yes Datasets. We compared across standard benchmark citation network datasets: Cora, Citeseer, and Pubmed with papers as nodes and citations as edges (Sen et al., 2008).
Dataset Splits Yes For each family, 300 graph instances were sampled with each instance having 10−20 nodes and evenly split into train/validation/test instances. In our experiments, we held out a set of 5% edges for validation, 10% edges for testing, and train all models on the remaining subgraph.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments, only mentioning general support from
Software Dependencies No The paper mentions general tools like
Experiment Setup No Additional hyperparameter details are described in Appendix B.