Research map / Label-efficient and robust learning / Self-supervised and contrastive
Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar
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 KREPES representer landmarks instead of latent cosine-similarity nearest neighbours | landmark retrieval · Adult | Precision@1: 80.9 -> 87.2 | Improved |
| use KREPES representer landmarks instead of latent cosine-similarity nearest neighbours | landmark retrieval · CoverType | Precision@1: 55.0 -> 77.2 | Improved |
| use Nystrom approximation instead of the full kernel (ablation) | KREPES · Adult and Bank | accuracy | No clear effect |
| delete top-10 KREPES-identified landmarks instead of random landmarks (ablation) | k-NN (k=50) on NN embeddings · inference-time latent ablation | prediction confidence drop | Improved |
| lower class coverage kappa_C of top-influence landmarks | KREPES representations · downstream classification | test accuracy | Improved |
| tune Barlow Twins regularization lambda to maximize spectral entropy of A^T A (ablation) | Barlow Twins KREPES · MNIST | linear probe accuracy | Improved |
Closest papers by meaning
- Improving Self-Supervised Learning by Characterizing Idealized Representations (NeurIPS 2022 · similarity 0.87)
- Non-parametric Representation Learning with Kernels (AAAI 2024 · similarity 0.86)
- Clustering Properties of Self-Supervised Learning (ICML 2025 · similarity 0.86)
- Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features (AAAI 2024 · similarity 0.85)
- Self-supervised Representation Learning from Random Data Projectors (ICLR 2024 · similarity 0.85)
- Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning (NeurIPS 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.
