The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models

Authors: Lee Gunderson, Gecia Bravo-Hermsdorff, Peter Orbanz

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental As shown in in figure 1, including these additional subgraphs can make the recovery of the SBM more robust.
Researcher Affiliation Academia Lee M. Gunderson Gatsby Unit University College London Gecia Bravo-Hermsdorff Department of Statistics University College London Peter Orbanz Gatsby Unit University College London
Pseudocode No The paper provides mathematical formulations and descriptions of its method but does not include any explicit pseudocode or algorithm blocks.
Open Source Code Yes Code implementing our method is available at https://github.com/The Grav Lab/The Graph Pencil Method.
Open Datasets No The paper states, 'We use 2-by-2 SBMs with varying degrees of assortativity to compare our basic method...', indicating synthetic data generated from SBMs for the experiments, rather than a publicly available dataset with concrete access information.
Dataset Splits No The paper evaluates its method using generated SBMs and presents results in Figure 1, but it does not specify any train/validation/test dataset splits or cross-validation methodologies typical for model training or evaluation on fixed datasets.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory, cloud instances) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, or other libraries and their versions) required to reproduce the experiments. While code is provided, the paper text itself lacks these details.
Experiment Setup Yes We use 2-by-2 SBMs with varying degrees of assortativity to compare our basic method using bistars from section 4.2 (green squares) and the method that adds the two-hop subgraphs from section 4.3 (purple circles). The vertical axis measures the expected squared error of the probability of an edge between two random nodes, and shading denotes 1 standard deviation from the average value.