Research map / Label-efficient and robust learning / Recognition and long-tail
Author Name Disambiguation on Heterogeneous Information Network with Adversarial Representation Learning
Haiwen Wang, Ruijie Wan, Chuan Wen, Shuhao Li, Yuting Jia, Weinan Zhang, Xinbing Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use the adversarial representation model rather than AMiner | Author name disambiguation · AMiner-AND | F1: 67.79 -> 72.92 | Improved |
| Use the adversarial representation model rather than Zhang and Al | Author name disambiguation · AceKG-AND | F1: 60.71 -> 73.71 | Improved |
| Add content representation to the generator-stage model instead of using content representation alone (ablation) | Gen on AMiner-AND · AMiner-AND | F1: 11.30 -> 72.92 | Improved |
| Add relation representation and adversarial learning rather than relation representation alone (ablation) | Gen on AMiner-AND · AMiner-AND | F1: 56.34 -> 72.92 | Improved |
| Add the generator stage after the discriminator stage (ablation) | Adversarial model · AMiner-AND | F1: 68.00 -> 72.92 | Improved |
| Add relation representation and adversarial learning rather than relation representation alone (ablation) | Gen on AceKG-AND · AceKG-AND | F1: 53.65 -> 73.71 | Improved |
| Add the generator stage after the discriminator stage (ablation) | Adversarial model · AceKG-AND | F1: 65.41 -> 73.71 | Improved |
| Use content representation alone rather than the generator-stage model (ablation) | Author name disambiguation · AceKG-AND | F1: 73.71 -> 55.40 | Hurt |
Closest papers by meaning
- Generative Adversarial Network Based Heterogeneous Bibliographic Network Representation for Personalized Citation Recommendation (AAAI 2018 · similarity 0.86)
- A Recurrent Model for Collective Entity Linking with Adaptive Features (AAAI 2020 · similarity 0.85)
- Task-Specific Representation Learning for Web-Scale Entity Disambiguation (AAAI 2018 · similarity 0.85)
- RMIB: Representation Matching Information Bottleneck for Matching Text Representations (ICML 2024 · similarity 0.82)
- RouterRetriever: Routing over a Mixture of Expert Embedding Models (AAAI 2025 · similarity 0.82)
- Revisit and Outstrip Entity Alignment: A Perspective of Generative Models (ICLR 2024 · similarity 0.82)
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.
