Research map / Graph learning / Graph self-supervised learning
Adversarial Network Embedding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add adversarial regularization to IDW (ablation) | AIDW · Cora, Citeseer, and Wiki node classification (10%–90% labeled) | accuracy: Cora: 66.32 -> 76.93 (10% labeled); Citeseer: 45.45 -> 53.25 (10% labeled); Wiki: 56.01 -> 57.43 (10% labeled) | Helped |
| Add adversarial regularization to DAE (ablation) | ADAE · Cora node classification | accuracy: 75.21 -> 75.01 (10% labeled); 80.91 -> 81.64 (50% labeled); 83.32 -> 84.10 (90% labeled) | Mixed |
| Add adversarial regularization to DAE (ablation) | ADAE · Citeseer node classification | accuracy: 51.08 -> 52.40 (10% labeled); 57.47 -> 58.34 (50% labeled); 60.15 -> 61.31 (90% labeled) | Helped |
| Add adversarial regularization to DAE (ablation) | ADAE · Wiki node classification | accuracy: 57.08 -> 57.24 (10% labeled); 66.84 -> 66.67 (50% labeled); 69.45 -> 70.59 (90% labeled) | Mixed |
| Use a Gaussian prior instead of a Uniform prior (ablation) | AIDW · Cora node classification | accuracy | No clear effect |
| Increase representation dimension from 8 toward 512 (ablation) | AIDW · Cora node classification (50% training) | accuracy | Helped |
| Vary walk length from 40 to 100 (ablation) | AIDW · Cora node classification (50% training) | accuracy | No clear effect |
| Increase context size beyond 6 (ablation) | AIDW · Cora node classification (50% training) | accuracy | Hurt |
Closest papers by meaning
- Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions (NeurIPS 2023 · similarity 0.90)
- Adversarial Attacks on Node Embeddings via Graph Poisoning (ICML 2019 · similarity 0.90)
- Unsupervised Adversarially Robust Representation Learning on Graphs (AAAI 2022 · similarity 0.89)
- Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning (CVPR 2020 · similarity 0.89)
- GraphGAN: Graph Representation Learning With Generative Adversarial Nets (AAAI 2018 · similarity 0.88)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.