Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges
Authors: Meixia He, Peican Zhu, Keke Tang, Yangming Guo
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments are conducted on five authentic datasets to validate the effectiveness of IE-Attack and the corresponding superiority to state-of-the-art methods. |
| Researcher Affiliation | Academia | 1School of Artificial Intelligence, Optics and Electronics (i OPEN), Northwestern Polytechnical University 2Cyberspace Institute of Advanced Technology, Guangzhou University 3Huangpu Research School, Guangzhou University 4School of Cybersecurity, Northwestern Polytechnical University |
| Pseudocode | No | The paper describes the methodology using mathematical equations and textual explanations, but it does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code for the described methodology, nor does it include any links to code repositories. |
| Open Datasets | Yes | To validate the superiority of our method, five datasets (Cora, Citeseer, Pubmed, Chameleon, Lastfm) (Maurya, Liu, and Murata 2021) are adopted. |
| Dataset Splits | Yes | According to the datasets partitioning strategy for node classification in Graph Convolutional Networks (GCNs) (Kipf and Welling 2017), datasets are divided into training/validation/test sets. |
| Hardware Specification | Yes | All experiments are conducted on a workstation equipped with four NVIDIA RTX 3090 GPUs, which are conducted under the same parameter settings. |
| Software Dependencies | No | The paper mentions software like HGNNs and GCNs, but does not provide specific version numbers for any libraries, frameworks, or programming languages used. |
| Experiment Setup | Yes | Parameter Setting In this study, we set the elite hyperedge perturbation budget η, which involves selecting η ω hyperedges within elite hyperedge Eelite. The value of η ranges from 0.1 to 1 and ω is the number of Eelite. Regarding the value of K in the Hyper-KNN hypergraph construction method, we set it to 10. The order in Hyper-HOR is set to 1-order and γ in Hyper-L1 is set to 0.1. ... Except for Table 1, the random seed for other experiments is set 2024. |