CONGREGATE: Contrastive Graph Clustering in Curvature Spaces

Authors: Li Sun, Feiyang Wang, Junda Ye, Hao Peng, Philip S. Yu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results on real-world graphs show that our model outperforms the state-of-the-art competitors. Experiments. We evaluate the superiority of our model with 19 strong competitors on 4 datasets, examine the proposed components by ablation study, and further discuss why Ricci curvature works.
Researcher Affiliation Academia 1North China Electric Power University, Beijing 102206, China 2Beijing University of Posts and Telecommunications, Beijing 100876, China 3Beihang University, Beijing 100191, China 4Department of Computer Science, University of Illinois at Chicago, IL, USA
Pseudocode Yes Algorithm 1: Training CONGREGATE
Open Source Code Yes Further details and code are provided https://github.com/Curv Cluster/Congregate.
Open Datasets Yes To evaluate the proposed model, we choose 4 public datasets, i.e., Cora and Citeseer [Devvrit et al., 2022], and larger MAG-CS [Park et al., 2022] and Amazon-Photo [Li et al., 2022].
Dataset Splits No The paper does not provide specific percentages or sample counts for training, validation, or test splits.
Hardware Specification No The paper does not provide specific hardware details such as CPU/GPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper mentions 'Riemannian Adam [Kochurov et al., 2020]' which implies a PyTorch dependency from the cited work, but it does not explicitly state specific version numbers for software libraries or dependencies.
Experiment Setup Yes The grid search is performed over search spaces for the hyperparameters, e.g., learning rate: [0.001, 0.003, 0.005, 0.008, 0.01], dropout rate: [0.0, 0.1, 0.2, 0.3, 0.4]. We utilize a 2-layer MLP to approximate the fine-grained curvature. In RGC loss, hyperparameter β of the reweighting is 2 as default.