Sparse Hypergraph Community Detection Thresholds in Stochastic Block Model
Authors: Erchuan Zhang, David Suter, Giang Truong, Syed Zulqarnain Gilani
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we confirm the positive part of the conjecture, the possibility of non-trivial reconstruction above the threshold, for the case of two blocks. We do so by comparing the hypergraph stochastic block model with its Erdös-Rényi counterpart. We also obtain estimates for the parameters of the hypergraph stochastic block model. The methods developed in this paper are generalised from the study of sparse random graphs by Mossel et al. 2015 and are motivated by the work of Yuan et al. 2022. Furthermore, we present some discussion on the negative part of the conjecture, i.e., non-reconstruction of community structures. Our work addresses (a), which does not imply any way to find an estimator of the partition for (b). |
| Researcher Affiliation | Academia | Erchuan Zhang School of Science Edith Cowan University erchuan.zhang@ecu.edu.au David Suter School of Science Edith Cowan University d.suter@ecu.edu.au Giang Truong School of Science Edith Cowan University h.truong@ecu.edu.au Syed Zulqarnain Gilani School of Science Edith Cowan University s.gilani@ecu.edu.au |
| Pseudocode | No | The paper contains mathematical derivations and proofs but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any links to open-source code or state that code for the described methodology is released. The checklist also indicates '[N/A]' for code. |
| Open Datasets | No | The paper is theoretical and does not use or reference any datasets for training or experimentation. The checklist indicates '[N/A]' for data. |
| Dataset Splits | No | The paper is theoretical and does not involve experimental validation with data splits. The checklist indicates '[N/A]' for training details. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setup that would require hardware specifications. The checklist indicates '[N/A]' for compute resources. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies with version numbers. The checklist indicates '[N/A]' for code and data assets. |
| Experiment Setup | No | The paper is theoretical and focuses on mathematical analysis rather than empirical experiments, hence no experimental setup details like hyperparameters or training configurations are provided. The checklist indicates '[N/A]' for training details. |