Characterizing the Influence of Graph Elements

Authors: Zizhang Chen, Peizhao Li, Hongfu Liu, Pengyu Hong

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

Reproducibility Variable Result LLM Response
Research Type Experimental We conducted three major experiments: (1) Validate the estimation accuracy of our influence functions on graph in Section 5.2; (2) Utilize the estimated edge influence to carry out adversarial attacks and graph rectification for increasing model performance in Section 5.3; and (3) Utilize the estimated node influence to carry out adversarial attacks on GCN (Kipf & Welling, 2017) in Section 5.4.
Researcher Affiliation Academia Zizhang Chen, Peizhao Li, Hongfu Liu, Pengyu Hong Brandeis University {zizhang2,peizhaoli,hongfuliu,hongpeng}@brandeis.edu
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code is publicly available at https://github.com/Cyrus9721/Characterizing_ graph_influence.
Open Datasets Yes We choose six real-world graph datasets:Cora, Pub Med, Cite Seer (Sen et al., 2008), Wi Ki CS (Mernyei & Cangea, 2020), Amazon Computers, and Amazon Photos (Shchur et al., 2018) in our experiments.
Dataset Splits Yes For the Cora, Pub Med, and Cite Seer datasets, we used their public train/val/test splits. For the Wiki-CS datasets, we took a random single train/val/test split provided by Mernyei & Cangea (2020). For the Amazon datasets, we randomly selected 20 nodes from each class for training, 30 nodes from each class for validation and used the rest nodes in the test set.
Hardware Specification No Table 2: Grey-box attacks to GCN via edge removals. A lower performance indicates a more successful attack. The best attacks are in bold font. The number following the dataset name is the preattack performance. denotes an out-of-memory issue encountered on GPU with 24GB VRAM.
Software Dependencies No The paper does not provide specific version numbers for software dependencies such as libraries, frameworks, or programming languages.
Experiment Setup No The paper mentions fine-tuning the model ("fine-tune it on the public split validation set") and describes general experimental procedures for attacks and rectification. However, it does not explicitly state specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or detailed system-level training configurations in the main text.