AI Paper Atlas

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

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 12 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 SimplEx mixture weights instead of KNN Uniform/Distance baselines for corpus decompositionlatent representation approximation · SEER prostate cancer and MNISTR2 in latent and output spaceImproved
use SimplEx instead of representer theorem for output approximationcorpus decomposition · SEER and MNISTR2_Y: -(7.2 \pm 6.6) for representer on MNISTImproved
increase number of corpus examples K beyond ~5 for KNN baselines (ablation)KNN baselines · SEER and MNISTR2Hurt
use Jacobian Projections instead of Integrated Gradients to select pixels to corruptSimplEx corpus · MNIST corpus of 500increase in corpus residualImproved
use SimplEx corpus residual to detect UK patients versus KNN baselinesclinical risk model · SEER (USA) vs UK patientsdetection of UK examplesImproved

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