CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
Authors: Han Chen, Ziwen Zhao, Yuhua Li, Yixiong Zou, Ruixuan Li, Rui Zhang
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We report extensive experiment results on three downstream tasks: node classification, node clustering, and link prediction. CSGCL achieves state-of-the-art performance compared with other GCL methods, validating that community strength brings effectiveness and generality to graph representations. Our code is available at https://github.com/Han Chen-HUST/ CSGCL.In this section, we describe our experiments that were conducted to evaluate our model and answer the questions below:Does GCL really benefit from our proposed methods? (Section 4.2).Is the boost to performance really given by community strength? (Section 4.3).How does the Team-up strength coefficient influence the performance on a certain graph? (Section 4.4).Detailed experiment configurations can be found in Appendix C. Additional experiment results using different community detectors and metrics (micro& macro-F1 and average precision) can be found in Appendix E. |
| Researcher Affiliation | Academia | Han Chen1,2 , Ziwen Zhao1 , Yuhua Li1, , Yixiong Zou1 , Ruixuan Li1 and Rui Zhang3, ,1School of Computer Science and Technology, Huazhong University of Science and Technology 2Institute of Artificial Intelligence, Huazhong University of Science and Technology 3Tsinghua University |
| Pseudocode | Yes | For an intuitive workflow of CSGCL, we summarize our approaches in pseudo-codes in Appendix A. |
| Open Source Code | Yes | Our code is available at https://github.com/Han Chen-HUST/ CSGCL. |
| Open Datasets | Yes | Datasets. We use four benchmark graphs in different fields, including one directed graph: Wiki-CS; and three undirected graphs: Amazon-Computers (Computers), Amazon-Photo (Photo), and Coauthor-CS. |
| Dataset Splits | Yes | For node classification, we follow the evaluation protocol of [Zhu et al., 2021] which trains and tests an ℓ2-regularized logistic regression classifier with 10 random data splits (20 fixed splits for Wiki-CS). |
| Hardware Specification | No | The paper mentions 'OOM stands for Out-Of-Memory on an 11GB GPU' but this is a general observation about a baseline model, not a specification of the hardware used for their own experiments. It also states 'Detailed environment configurations can be found in Appendix C.2', implying hardware details might be there, but they are not in the main paper text provided. |
| Software Dependencies | No | The paper states 'A simple two-layer GCN is employed to CSGCL as well as all other contrastive baselines. We use the Adam optimizer to optimize the model. Detailed environment configurations can be found in Appendix C.2.' It mentions GCN and Adam optimizer but does not specify versions for any software or libraries. |
| Experiment Setup | Yes | Detailed experiment configurations can be found in Appendix C.2. Implementation details. We choose Leiden [Traag et al., 2019] as the community detector for CSGCL, before which we pretested the community detection methods detailed in Appendix E.1. To ensure fairness, A simple two-layer GCN is employed to CSGCL as well as all other contrastive baselines. We use the Adam optimizer to optimize the model. |