paper-with-me

홈 › Papers

Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams

2022-09-05 · Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier, Barbara Hammer

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.

📄 PDF Abstract BibTeX arXiv:2209.01939

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature Importance

Similar Papers 제목 키워드 기반

TRIP: A Nonparametric Test to Diagnose Biased Feature Importance Scores

2025-07-09 · Aaron Foote, Danny Krizanc arxiv

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 Importance

Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP

2026-08-02 · Jiaan Han, Junxiao Chen, Yanzhe Fu arxiv

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

2026-02-26 · Yu Zhang, Songwei Liu, Chenqian Yan, Sheng Lin 외 arxiv

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

2026-04-13 · Emanuele Borgonovo, Francesco Cappelli, Xuefei Lu, Elmar Plischke 외 arxiv

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 Importance

Classifying Unordered Feature Sets with Convolutional Deep Averaging Networks

2017-09-10 · Andrew Gardner, Jinko Kanno, Christian A. Duncan, Rastko R. Selmic

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…