Escaping Feature Twist: A Variational Graph Auto-Encoder for Node Clustering

Authors: Nairouz Mrabah, Mohamed Bouguessa, Riadh Ksantini

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct various experiments to validate the contributions of the proposed approach. The obtained results provide strong evidence that our model can improve the clustering performance over several state-of-the-art deep graph clustering methods by escaping Feature Twist.
Researcher Affiliation Academia Nairouz Mrabah1 , Mohamed Bouguessa1 and Riadh Ksantini2 1University of Quebec at Montreal, Montreal, QC, Canada 2University of Bahrain, Kingdom of Bahrain
Pseudocode No The full algorithm and its complexity analysis are provided in Appendix F and Appendix G, respectively, due to page limit restrictions.
Open Source Code Yes Our code is available on https://github.com/nairouz/FT-VGAE.
Open Datasets Yes We select six datasets for our experiments: three citation networks [Sen et al., 2008] (Cora, Citeseer, and Pubmed) and three air traffic networks [Sen et al., 2008] (Brazil Air Traffic, US Air Traffic, and Europe Air Traffic).
Dataset Splits No No explicit dataset splits (e.g., percentages, counts) for training, validation, or testing were found in the main text of the paper. Details are deferred to Appendix I.
Hardware Specification No All experiments are performed under the same hardware and software environments as described in Appendix J. Specific hardware details are not provided in the main text.
Software Dependencies No All experiments are performed under the same hardware and software environments as described in Appendix J. Specific software dependencies with version numbers are not provided in the main text.
Experiment Setup No The architecture, learning rates, and all the other hyper-parameters of FT-VGAE are specified and discussed in Appendix H. These details are not in the main text.