Graph Debiased Contrastive Learning with Joint Representation Clustering
Authors: Han Zhao, Xu Yang, Zhenru Wang, Erkun Yang, Cheng Deng
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on five datasets demonstrate that our method achieves new state-of-the-art results on graph clustering and classification tasks. |
| Researcher Affiliation | Academia | Han Zhao , Xu Yang , Zhenru Wang , Erkun Yang and Cheng Deng Xidian University {hzhao1698, xuyang.xd, zhenruwang1997, erkunyang, chdeng.xd}@gmail.com |
| Pseudocode | Yes | Algorithm 1 Graph Debiased Contrastive Learning Input: Graph G, Maximum Iterations Max Iter Parameter: GCN parameter Θ, hyper-parameter: sample size of negative points M Output: Optimized GCN parameters, clustering results. 1: Initialize Θ, {µj}C j=1 according to Section 4.2. 2: while iter {0, 1, ..., Max Iter} do 3: if iter%T == 0 then 4: Embed node representations by gΘ( ) 5: Update P by Equation 4. 6: end if 7: Generate Yp by clustering layer. 8: Update {Ni}n i=1by Equation 8. 9: Update Θ, {µj}C j=1 by Equation 6 and 7. 10: end while |
| Open Source Code | No | The paper does not provide concrete access information (specific link, explicit statement of release, or mention in supplementary materials) for the source code. |
| Open Datasets | Yes | For comparison, we select five widely used graph datasets to verify the performance of our method in unsupervised representation learning. Specifically, for node classification and clustering, there are three citation network datasets, i.e., Cora, Citeseer and Pubmed. Moreover, for graph classification, we use two datasets: MUTAG and PTC-MR. |
| Dataset Splits | Yes | Finally, for graph classification, we follow MVGRL [Hassani and Khasahmadi, 2020] and report the mean 10-fold cross validation accuracy with standard deviation after 5 runs. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | Implementation Details. Following suggestions in [Guo et al., 2017], we pretrain the contrastive learning framework before perform debiased strategy. And the cluster centers {µj}C j=1 are initialized by employing clustering layer on gΘ(X). For node clustering task, one-layer GCN is used in the graph contrastive framework and the hidden dimension of GCN is set to 220. The learning rate is set to 0.0001 on Cora and Citeseer, 0.00004 on Pubmed. The hyper-parameter α is set to 0.1 on Cora and Pubmed, 0.5 on Citeseer. For the node classification task, the learning rate is set to 0.01 on all three datasets when optimize the classification layer. For the graph classification task, the hidden dimension of GCN is 512, α is set to 0.3 on MUTAG and PTC-MR datasets. |