Summary of Rw-nsgcn: a Robust Approach to Structural Attacks Via Negative Sampling, by Shuqi He et al.
RW-NSGCN: A Robust Approach to Structural Attacks via Negative Sampling
by Shuqi He, Jun Zhuang, Ding Wang, Jun Song
First submitted to arxiv on: 13 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 paper proposes a novel method called Random Walk Negative Sampling Graph Convolutional Network (RW-NSGCN) to improve the robustness of Node classification using Graph Neural Networks (GNNs). This is particularly important in social networks where potential noise and attacks can lead to decreased classification performance. The RW-NSGCN model integrates Random Walk with Restart (RWR), PageRank (PGR), and Determinantal Point Process (DPP)-based GCN for negative sampling, topological structure stabilization, and diversity aggregation. Experimental results show that the proposed method effectively addresses network topology attacks and weight instability, leading to increased accuracy of anomaly detection and overall stability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make sure Graph Neural Networks are good at predicting things in social networks. Sometimes, these networks can have bad information in them that makes it harder for GNNs to work well. The new method, called RW-NSGCN, helps by using different ways to find patterns and ignore noise. This makes the GNNs better at detecting weird things and more stable overall. |
Keywords
» Artificial intelligence » Anomaly detection » Classification » Convolutional network » Gcn
