Research map / Graph learning / Graph self-supervised learning
DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space
Songlin Zhai, Weiqing Wang, Yuanfang Li, Yuan Meng
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 DNG instead of TaxoEnrich | Taxonomy expansion · MAG-CS | Recall@1: 0.182 -> 0.268 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · MAG-CS | Precision@1: 0.304 -> 0.317 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · MAG-CS | MR: 67.947 -> 59.354 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · MAG-CS | MRR: 0.721 -> 0.754 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · WordNet-Verb | Recall@1: 0.162 -> 0.199 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · WordNet-Verb | Precision@1: 0.294 -> 0.201 | Hurt |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · WordNet-Verb | MR: 217.842 -> 43.723 | Improved |
| Use DNG instead of TaxoEnrich | Taxonomy expansion · WordNet-Verb | MRR: 0.481 -> 0.513 | Improved |
| Use a non-Gaussian rather than Gaussian supplementary-feature distribution | DNG · Synthetic four-node taxonomy | mean deviation-degree ratio: 45.56% -> 107.19% | Improved |
Closest papers by meaning
- Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies (ICLR 2026 · similarity 0.86)
- Learning Taxonomy Adaptation in Large-scale Classification (JMLR 2016 · similarity 0.86)
- QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion (AAAI 2026 · similarity 0.85)
- Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery (NeurIPS 2025 · similarity 0.83)
- Taxonomy-Aware Evaluation of Vision-Language Models (CVPR 2025 · similarity 0.82)
- What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits (ICLR 2025 · 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.
