Summary of Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification, by Honglin Gao and Gaoxi Xiao
Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
by Honglin Gao, Gaoxi Xiao
First submitted to arxiv on: 4 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed HeteroKRLAttack is a targeted evasion black-box attack method that efficiently identifies effective attack strategies to disrupt node classification tasks on heterogeneous graphs. By integrating reinforcement learning with a Top-K algorithm, the approach reduces the action space and improves attack performance. The paper validates the effectiveness of HeteroKRLAttack through experiments on multiple heterogeneous graph datasets, demonstrating significant reductions in classification accuracy compared to baseline methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Heterogeneous graphs are important for modeling complex systems, but they’re vulnerable to attacks that disrupt node classification tasks. Researchers have developed a new attack method called HeteroKRLAttack that can target these graphs and make it harder for models to classify nodes accurately. This attack uses reinforcement learning to find the best way to mislead the model. Tests on several datasets showed that this attack was very effective in reducing classification accuracy. |
Keywords
» Artificial intelligence » Classification » Reinforcement learning
