G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns
Authors: Qin Zhang, Zelin Shi, Xiaolin Zhang, Xiaojun Chen, Philippe Fournier-Viger, Shirui Pan
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments were conducted to validate the performance of G2Pxy. These experiments include: open-set node classification comparison, ablation study, and use case. Codes are available online1. Datasets. Experiments to evaluate the performance for open-set node classification were mainly carried out on four benchmark graph datasets [Wu et al., 2020; Zhu et al., 2022], namely Cora2, Citeseer3, DBLP4, Pub Med5, which are widely used citation network datasets. Statistics are presented in Table 1. |
| Researcher Affiliation | Collaboration | Qin Zhang1, Zelin Shi1, Xiaolin Zhang2 , Xiaojun Chen1, Philippe Fournier-Viger1, and Shirui Pan3 1Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, China 2Sensetime 3School of Information and Communication Technology, Griffith University, Queensland, Australia |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Codes are available online1. 1https://github.com/ejfomxhue2o3239djnwkk/G2Pxy |
| Open Datasets | Yes | Cora2, Citeseer3, DBLP4, Pub Med5, which are widely used citation network datasets. Statistics are presented in Table 1. 2https://graphsandnetworks.com/the-cora-dataset/ 3https://networkrepository.com/citeseer.php 4https://dblp.uni-trier.de/xml/ 5https://pubmed.ncbi.nlm.nih.gov/download/ |
| Dataset Splits | Yes | 70% of the known class nodes were sampled for training, 10% for validation and 20% for testing. |
| Hardware Specification | Yes | All the experiments were conducted on a workstation equipped with an Intel(R) Xeon(R) Gold 6226R CPU and an Nvidia A100. |
| Software Dependencies | No | The paper mentions "PyTorch" as an implementation framework but does not provide a specific version number for it or other software dependencies. |
| Experiment Setup | Yes | The GCN is configured with two hidden GCN layers in the dimensions of 512 and 128, followed by an additional multilayer perceptron layer of size 64. G2Pxy is implemented with Py Torch and the networks are optimized using stochastic gradient gradient descent with a learning rate of 1e 3. The balance parameters λ1 and λ2 are chosen by a grid search in the interval from 10 2 to 102 with a step size of 101. |