Multi-view Contrastive Graph Clustering

Authors: ErLin Pan, Zhao Kang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Results on several benchmark datasets show the superiority of our method with respect to state-of-the-art approaches.
Researcher Affiliation Academia Erlin Pan, Zhao Kang School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China wujisixsix6@gmail.com zkang@uestc.edu.cn
Pseudocode Yes Algorithm 1 MCGC
Open Source Code Yes The implementation of MCGC is public available 1. 1https://github.com/Panern/MCGC
Open Datasets Yes We evaluate MCGC on fve benchmark datasets, ACM, DBLP, IMDB [Fan et al., 2020], Amazon photos and Amazon computers [Shchur et al., 2018].
Dataset Splits No The paper lists benchmark datasets but does not explicitly provide details on how the data was split into training, validation, and test sets (e.g., specific percentages, sample counts, or explicit references to predefined splits with citations).
Hardware Specification Yes All experiments are conducted on the same machine with the Intel(R) Core(TM) i7-8700 3.20GHz CPU, two Ge Force GTX 1080 Ti GPUs and 64GB RAM.
Software Dependencies No The paper mentions the use of Adam optimization strategy and provides a link to its implementation code, but it does not explicitly list specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks with their versions).
Experiment Setup Yes During experiments, k = 10 is used to select neighbors and γ is fxed as 4 since we fnd that it has little infuence to the result. According to parameter analysis, we set m = 2, s = 0.5, and tune α. Afterwards, we tune the trade-off parameter α = [10 3 , 0.1, 1, 10, 102 , 103].