Research map / Label-efficient and robust learning / Recognition and long-tail

Elastic Representations via Hyperbolic Geometry

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an elastic representation method based on hyperbolic geometry that aims to support flexible embedding sizes without costly retraining, as an alternative to Matryoshka Representation Learning.

Problem

Learned embeddings are usually trained at a fixed size, ignoring varying downstream resource or task constraints. Matryoshka Representation Learning (MRL) yields nested representations but needs costly end-to-end retraining and does not support post hoc expansion.

Approach

Uses hyperbolic geometry to learn elastic (nested) representations; the abstract states the goal of supporting post hoc expansion, but the method details are not available in the provided text.

Experimental setup

Baselines: Matryoshka Representation Learning

Builds on: Matryoshka Representation Learning

Closest papers by meaning

• Hyperbolic Representation Learning: Revisiting and Advancing (ICML 2023 · similarity 0.92)
• Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning (ICML 2025 · similarity 0.91)
• Adaptive Hyperbolic Kernels: Modulated Embedding in de Branges-Rovnyak Spaces (AAAI 2026 · similarity 0.89)
• Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation (ICML 2025 · similarity 0.89)
• Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.88)
• Robust Hyperbolic Learning with Curvature-Aware Optimization (NeurIPS 2025 · similarity 0.86)