AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Formal Abductive Latent Explanations for Prototype-Based Networks

Jules Soria, Zakaria Chihani, Julien Girard-Satabin, Alban Grastien, Romain Xu-Darme, Daniela Cancila

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 3 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 top-k (k=10) ProtoPNet-style explanationProtoPNet · all datasets except MNISTexplanation sufficiencyHurt
use spatial-constraint ALEs instead of top-kProtoPNet · CIFAR-10explanation size: 41.4 -> 8.7Improved
use hypersphere intersection instead of triangle inequality (ablation)ALE · Stanford Carsexplanation size: 5072.3 -> 24.9Improved
use hypersphere intersection instead of triangle inequality (ablation)ALE · CIFAR-10explanation size: 8.7 -> 20.2Hurt
use hypersphere intersection instead of triangle inequality (ablation)ALE · MNISTexplanation size: 6.2 -> 675Hurt
incorrect vs correct predictionsALE triangle · CUB200explanation size: 670.9 -> 98000Hurt
incorrect vs correct predictionsALE triangle · CIFAR-10explanation size: 6.6 -> 19.4Hurt
formal guarantees on prototype explanationsALE · high-resolution fine-grained datasetsexplanation size: thousands of pairsHurt

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