Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Sheaf Hypergraph Networks
Authors: Iulia Duta, Giulia Cassarà, Fabrizio Silvestri, Pietro Lió
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through extensive experimentation, we show that this generalization significantly improves performance, achieving top results on multiple benchmark datasets for hypergraph node classification. |
| Researcher Affiliation | Academia | Iulia Duta University of Cambridge EMAIL Giulia Cassarà University of Rome, La Sapienza EMAIL Fabrizio Silvestri University of Rome, La Sapienza EMAIL Pietro Liò University of Cambridge EMAIL |
| Pseudocode | No | The paper describes computational procedures but does not include formal pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide a direct link or explicit statement for the availability of the source code for its own methodology. The only code link refers to a baseline method, HNHN: “Code available: https://github.com/twistedcubic/HNHN.” which is not their own work. |
| Open Datasets | Yes | We evaluate our model on eight real-world datasets that vary in domain, scale, and heterophily level and are commonly used for benchmarking hypergraphs. These include Cora, Citeseer, Pubmed, Cora-CA, DBLP-CA [37], House [52], Senate and Congress [53]. |
| Dataset Splits | Yes | To ensure a fair comparison with the baselines, we follow the same training procedures used in [50] by randomly splitting the data into 50% training samples, 25% validation samples and 25% test samples, and running each model 10 times with different random splits. |
| Hardware Specification | Yes | The experiments are executed on a single NVIDIA Quadro RTX 8000 with 48GB of GPU memory. |
| Software Dependencies | No | The paper mentions “PyTorch” indirectly when discussing a fix for Hyper GCN code, but does not provide specific version numbers for PyTorch or any other software dependencies used in its experiments. |
| Experiment Setup | No | Details on all the model choices and hyper-parameters can be found in the Supplementary Material. |