Research map / Label-efficient and robust learning / Recognition and long-tail
Explaining Latent Representations with a Corpus of Examples
Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela van der Schaar
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 SimplEx mixture weights instead of KNN Uniform/Distance baselines for corpus decomposition | latent representation approximation · SEER prostate cancer and MNIST | R2 in latent and output space | Improved |
| use SimplEx instead of representer theorem for output approximation | corpus decomposition · SEER and MNIST | R2_Y: -(7.2 \pm 6.6) for representer on MNIST | Improved |
| increase number of corpus examples K beyond ~5 for KNN baselines (ablation) | KNN baselines · SEER and MNIST | R2 | Hurt |
| use Jacobian Projections instead of Integrated Gradients to select pixels to corrupt | SimplEx corpus · MNIST corpus of 500 | increase in corpus residual | Improved |
| use SimplEx corpus residual to detect UK patients versus KNN baselines | clinical risk model · SEER (USA) vs UK patients | detection of UK examples | Improved |
Closest papers by meaning
- Representational Difference Explanations (NeurIPS 2025 · similarity 0.84)
- I-CEE: Tailoring Explanations of Image Classification Models to User Expertise (AAAI 2024 · similarity 0.83)
- Data-centric Prediction Explanation via Kernelized Stein Discrepancy (ICLR 2025 · similarity 0.83)
- Learning Discrete Concepts in Latent Hierarchical Models (NeurIPS 2024 · similarity 0.83)
- LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs (ICML 2026 · similarity 0.83)
- From Causal to Concept-Based Representation Learning (NeurIPS 2024 · similarity 0.82)
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.
