AI Paper Atlas

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

ICML 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use KREPES representer landmarks instead of latent cosine-similarity nearest neighbourslandmark retrieval · AdultPrecision@1: 80.9 -> 87.2Improved
use KREPES representer landmarks instead of latent cosine-similarity nearest neighbourslandmark retrieval · CoverTypePrecision@1: 55.0 -> 77.2Improved
use Nystrom approximation instead of the full kernel (ablation)KREPES · Adult and BankaccuracyNo clear effect
delete top-10 KREPES-identified landmarks instead of random landmarks (ablation)k-NN (k=50) on NN embeddings · inference-time latent ablationprediction confidence dropImproved
lower class coverage kappa_C of top-influence landmarksKREPES representations · downstream classificationtest accuracyImproved
tune Barlow Twins regularization lambda to maximize spectral entropy of A^T A (ablation)Barlow Twins KREPES · MNISTlinear probe accuracyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy