Adversarial Attacks on Node Embeddings via Graph Poisoning

Authors: Aleksandar Bojchevski, Stephan Günnemann

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4. Experimental Evaluation
Researcher Affiliation Academia 1Technical University of Munich, Germany.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code and data available at https://www.kdd.in.tum.de/node embedding attack.
Open Datasets Yes We analyze three datasets: Cora (N = 2810, |E| = 15962, Mc Callum et al. (2000); Bojchevski & G unnemann (2018)) and Citeseer (N = 2110, |E| = 7336, Giles et al. (1998)) are citation networks commonly used to benchmark embedding approaches, and Pol Blogs (N = 1222, |E| = 33428, Adamic & Glance (2005)) is a graph of political blogs.
Dataset Splits No The paper does not explicitly provide specific train/validation/test dataset splits or mention a validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library or solver names with version numbers).
Experiment Setup Yes We set Deep Walk s hyperparameters to: T = 5, b = 5, K = 64 and use logistic regression for classification.