We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Incremental permutation feature importance (iPFI): towards online explanations on data streams.
- Authors
Fumagalli, Fabian; Muschalik, Maximilian; Hüllermeier, Eyke; Hammer, Barbara
- Abstract
Explainable artificial intelligence has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and learning is done in an incremental rather than a batch mode. We seek efficient incremental algorithms for computing feature importance (FI). Permutation feature importance (PFI) is a well-established model-agnostic measure to obtain global FI based on feature marginalization of absent features. We propose an efficient, model-agnostic algorithm called iPFI to estimate this measure incrementally and under dynamic modeling conditions including concept drift. We prove theoretical guarantees on the approximation quality in terms of expectation and variance. To validate our theoretical findings and the efficacy of our approaches in incremental scenarios dealing with streaming data rather than traditional batch settings, we conduct multiple experimental studies on benchmark data with and without concept drift.
- Subjects
PERMUTATIONS; ARTIFICIAL intelligence; DYNAMIC models; EXPLANATION
- Publication
Machine Learning, 2023, Vol 112, Issue 12, p4863
- ISSN
0885-6125
- Publication type
Article
- DOI
10.1007/s10994-023-06385-y