Research map / Label-efficient and robust learning / Recognition and long-tail
Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning
Sahil Mishra, Srinitish Srinivasan, Sourish Dasgupta, Tanmoy Chakraborty
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 Polaris polar hyperspherical embedding instead of strongest baseline | taxonomy expansion · Environment | Mean rank: 27.1 -> 6.48 | Improved |
| use Polaris instead of STEAM | taxonomy expansion · MeSH (multi-parent) | H@1: 18.2 -> 33.56 | Improved |
| use Polaris instead of STEAM | taxonomy expansion · MeSH (multi-parent) | mean rank: 372.6 -> 300.40 | Improved |
| use Polaris instead of STEAM | taxonomy expansion · SemEval-Food | R@1 and MRR | Hurt |
| use Polaris instead of STEAM | taxonomy expansion · SemEval-Verb | H@1: 12.6 -> 14.43 | Improved |
| use Polaris instead of Gumbel Box | image-to-label ranking · CUB-200-2011 subset | Precision@1: 73.93 -> 78.91 | Improved |
| use Polaris instead of STEAM | taxonomy expansion · Science | R@1: 34.8 -> 46.18 | Improved |
Closest papers by meaning
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry (ICML 2018 · similarity 0.86)
- Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy (NeurIPS 2026 · similarity 0.85)
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (AAAI 2020 · similarity 0.84)
- Hyperbolic Concept Bottleneck Models (NeurIPS 2026 · similarity 0.83)
- Learning Structured Representations with Hyperbolic Embeddings (NeurIPS 2024 · similarity 0.83)
- Banyan: Improved Representation Learning with Explicit Structure (ICML 2025 · similarity 0.83)
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.
