Research map / Label-efficient and robust learning / Recognition and long-tail
GANTEE: Generative Adversarial Network for Taxonomy Enterance Evaluation
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 GANTEE to TaxoExpan | TaxoExpan · MAG-CS | MRR@10: 0.319 -> 0.360 | Helped |
| Add GANTEE to TaxoExpan | TaxoExpan · MAG-CS | time: 471.4 s -> 152.8 s | Helped |
| Add GANTEE to TaxoExpan | TaxoExpan · MAG-FoS | MRR@100: 0.305 -> 0.382 | Helped |
| Add GANTEE to TaxoExpan | TaxoExpan · MAG-FoS | time: 25.2k s -> 6.1k s | Helped |
| Add GANTEE to TaxoExpan | TaxoExpan · CN-Probase | MRR@1k | Helped |
| Use GANTEE for entering evaluation instead of TaxoExpan | Taxonomy entering evaluation · MAG-CS | F1: 52.7 -> 79.3 | Helped |
| Use GANTEE for entering evaluation instead of TaxoExpan | Taxonomy entering evaluation · CN-Probase-Sampled | F1: 32.1 -> 65.4 | Helped |
| Add the hyper discriminator during adversarial generation (ablation) | GANTEE · MAG-CS taxonomy entering evaluation | F1: 62.9 -> 79.3 | Helped |
| Add the rollout discriminator during adversarial generation (ablation) | GANTEE · MAG-CS taxonomy expansion | MRR: 0.351 -> 0.360 | Helped |
| Use adversarial training instead of only the generator (ablation) | GANTEE · MAG-CS taxonomy entering evaluation | F1: 51.9 -> 79.3 | Helped |
Closest papers by meaning
- Taxonomy-Structured Domain Adaptation (ICML 2023 · similarity 0.86)
- Improving Hypernymy Prediction via Taxonomy Enhanced Adversarial Learning (AAAI 2019 · similarity 0.84)
- Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks (AAAI 2024 · similarity 0.83)
- Taxonomy-Aware Evaluation of Vision-Language Models (CVPR 2025 · similarity 0.82)
- Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery (NeurIPS 2025 · similarity 0.81)
- Hybrid Data-Free Knowledge Distillation (AAAI 2025 · similarity 0.81)
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.