Research map / Label-efficient and robust learning / Recognition and long-tail
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
Shuxiao Chen, Hangfeng He, Weijie Su
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 label-aware higher-order regression | CNTK · CIFAR-10 binary classification | test accuracy (Avg): 85.91 -> 86.95 | Improved |
| Add label-aware higher-order regression | CNTK · CIFAR-10 multi-class classification | test accuracy (Avg): 52.44 -> 54.38 | Improved |
| Add label-aware higher-order regression | NTK · CIFAR-10 train-train, frog vs ship | local elasticity RR: 63.83 -> 66.62 | Improved |
| Add label-aware higher-order regression | NTK · CIFAR-10 test-train, frog vs ship | local elasticity RR: 63.76 -> 66.53 | Improved |
| Approximate the time-varying kernel using the NTH construction | NTK · Neural tangent hierarchy approximation | approximation error | Improved |
Closest papers by meaning
- The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training (AAAI 2025 · similarity 0.87)
- Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training? (CVPR 2022 · similarity 0.86)
- The Recurrent Neural Tangent Kernel (ICLR 2021 · similarity 0.86)
- Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks (ICML 2024 · similarity 0.85)
- Neural Collapse in Multi-label Learning with Pick-all-label Loss (ICML 2024 · similarity 0.85)
- Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration (CVPR 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.
