Framework adds feature importance to prototype explanations: local 'alike parts' for shared subsets and global selection for feature diversity, with experiments showing maintained or improved surrogate fidelity on six benchmarks.
Advances in Neural Information Processing Systems , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
Framework adds feature importance to prototype explanations: local 'alike parts' for shared subsets and global selection for feature diversity, with experiments showing maintained or improved surrogate fidelity on six benchmarks.