Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
Explainable Artificial Intelligence (XAI) 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) measures, specifically, an incremental FI measure based on feature marginalization of absent features similar to permutation feature importance (PFI). 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 compared to traditional batch PFI, we conduct multiple experimental studies on benchmark data with and without concept drift.
Code (0)
등록된 구현이 없습니다.
Tasks
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature ImportanceSimilar Papers 제목 키워드 기반
TRIP: A Nonparametric Test to Diagnose Biased Feature Importance Scores
Along with accurate prediction, understanding the contribution of each feature to the making of the prediction, i.e., the importance of the feature, is a desirable and arguably necessary component of a machine learning m…
Feature ImportanceModel-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP
Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This abstraction fails in sequential and grouped models, where one or…
S2O: Early Stopping for Sparse Attention via Online Permutation
Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic sparsity ceiling, ma…
Trustworthy Feature Importance Avoids Unrestricted Permutations
Feature importance methods using unrestricted permutations are flawed due to extrapolation errors; such errors appear in all non-trivial variable importance approaches. We propose three new approaches: conditional model …
Feature ImportanceClassifying Unordered Feature Sets with Convolutional Deep Averaging Networks
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the lea…