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
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 top-k (k=10) ProtoPNet-style explanation | ProtoPNet · all datasets except MNIST | explanation sufficiency | Hurt |
| use spatial-constraint ALEs instead of top-k | ProtoPNet · CIFAR-10 | explanation size: 41.4 -> 8.7 | Improved |
| use hypersphere intersection instead of triangle inequality (ablation) | ALE · Stanford Cars | explanation size: 5072.3 -> 24.9 | Improved |
| use hypersphere intersection instead of triangle inequality (ablation) | ALE · CIFAR-10 | explanation size: 8.7 -> 20.2 | Hurt |
| use hypersphere intersection instead of triangle inequality (ablation) | ALE · MNIST | explanation size: 6.2 -> 675 | Hurt |
| incorrect vs correct predictions | ALE triangle · CUB200 | explanation size: 670.9 -> 98000 | Hurt |
| incorrect vs correct predictions | ALE triangle · CIFAR-10 | explanation size: 6.6 -> 19.4 | Hurt |
| formal guarantees on prototype explanations | ALE · high-resolution fine-grained datasets | explanation size: thousands of pairs | Hurt |
Closest papers by meaning
- Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning (AAAI 2024 · similarity 0.89)
- Deep Learning for Case-Based Reasoning Through Prototypes: A Neural Network That Explains Its Predictions (AAAI 2018 · similarity 0.89)
- Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space. (ICLR 2022 · similarity 0.88)
- Contextual Explanation Networks (JMLR 2020 · similarity 0.87)
- Think in Latent, Explain in Language: Self-Explainable Latent Reasoning (ICML 2026 · similarity 0.85)
- Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations (ICML 2025 · similarity 0.85)
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.
