Research map / Label-efficient and robust learning / Recognition and long-tail
Vector Linking via Cross-Model Local Isometric Consistency
Ziying Chen, Yang Cao, He Sun, Beining Yang, Tianjian Yang
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 |
|---|---|---|---|
| add bootstrapping of confident links as new anchors (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 1.9 -> 70.5 | Improved |
| add multi-view voting (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 29.8 -> 70.5 | Improved |
| add adaptive view scheduling (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 43.4 -> 70.5 | Improved |
| add FPS view sampling (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 20.9 -> 70.5 | Improved |
| add kernelized distance signature (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 51.0 -> 70.5 | Improved |
| add both FPS and kernel (ablation) | GEH · SciDocs ablation (alpha 0.15, 15 seeds) | F1 (%): 1.4 -> 70.5 | Improved |
| increase seed anchors from 15 to 30 (overlap .3) (ablation) | GEH · SciFact (Mistral-OpenAI) | F1 (%): 85.8 -> 85.3 | No clear effect |
| increase seed anchors from 15 to 30 (overlap .3) (ablation) | Procrustes · SciFact (Mistral-OpenAI) | F1 (%): 8.9 -> 40.1 | Improved |
| use GEH instead of CCA for linking | Mistral-OpenAI · FEVER (alpha 0.3, 30 seeds) | precision (%): 5.22 -> 93.8 | Improved |
| use kernelized encoding instead of raw distance (ablation) | GEH · SciDocs | precision/recall | Improved |
| use out-of-domain anchors instead of in-domain | GEH · OOD seeds (30, overlap 30%) | precision/recall (%): 77-87 precision, 80-97 recall | No clear effect |
Closest papers by meaning
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.85)
- When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product (NeurIPS 2025 · similarity 0.85)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.84)
- Towards an Explainable Comparison and Alignment of Feature Embeddings (ICML 2025 · similarity 0.84)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 2025 · similarity 0.84)
- Disentangled Representation Learning with the Gromov-Monge Gap (ICLR 2025 · similarity 0.84)
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.
