ADORE unifies global and local explanations with first/second derivatives; authors claim it beats LIME and SHAP
ADORE uses first- and second-order derivatives to capture nonlinear feature interactions, unifying global importance and local contributions in one framework; its authors self-report it outperforms LIME and SHAP and have open-sourced it.
ImportanceLocalEvidenceE2 unreplicated
Readers can now obtain global feature importance and local sample contributions within a single framework: ADORE uses first- and second-order derivatives to characterize nonlinear feature interactions, combined with randomized SVD and dynamic sparsity detection, covering tabular, text, and image data, with a Python package open-sourced.
Previously, getting both global and local explanations required separate tools such as LIME and SHAP; the authors self-report that ADORE outperforms both in interaction modeling and computational efficiency, though this comparison is the authors' own experimental conclusion.
The measurement was made by the authors themselves (first-party self-report): the benchmarks for their interaction-modeling and computational-efficiency comparison were LIME and SHAP, with ADORE reported as superior.
Boundary: the comparison has not been reproduced by third parties, and coverage is limited to the tabular, text, and image data the authors tested; Lemen Chao and two co-authors submitted it to arXiv on September 15 (v2 revised September 16, id 2609.17171).