Understanding Structural Vulnerability in Graph Convolutional Networks
Authors: Liang Chen, Jintang Li, Qibiao Peng, Yang Liu, Zibin Zheng, Carl Yang
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on four real-world datasets demonstrate that such a simple but effective method achieves the best robustness performance compared to state-of-the-art models. |
| Researcher Affiliation | Academia | 1Sun Yat-sen University 2Emory University |
| Pseudocode | No | The paper provides mathematical equations for the models but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | Yes | The codes are available at https://github.com/EdisonLeeeee/Median-GCN. |
| Open Datasets | Yes | The experiments are conducted on four benchmark datasets, including Cora-ML [Mc Callum et al., 2000], Cora, Citeseer and Pubmed [Sen et al., 2008] datasets. |
| Dataset Splits | Yes | The datasets are randomly split into training (10%), validation (10%), and testing (80%) set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using the Adam algorithm but does not specify software dependencies like libraries or frameworks with their version numbers (e.g., 'PyTorch 1.9', 'Python 3.8'). |
| Experiment Setup | Yes | The datasets are randomly split into training (10%), validation (10%), and testing (80%) set. For all models, the number of layers is set to 2 as suggested by previous works [Kipf and Welling, 2017; Velickovic et al., 2018] and the number of hidden units is 64. We employ Adam algorithm [Kingma and Ba, 2015] with an initial learning rate 0.01 to optimize all models. The number of training iterations is 200 with early stopping on the validation set. Following the setting of the work [Wu et al., 2019], the threshold of similarity for removing dissimilar edges is set to 0. The trimmed percentage α of our TMean is set to 0.45 to balance the accuracy and robustness. |