cs.LGNov 17, 2026

Right Labels, Wrong Reasons: Signed Feature Attribution for Multi-Label Explainability

Authors: Kenton White

Organizations: AC Online, Algonquin College, Ottawa, ON, Canada

Abstract

When a multi-label classifier assigns the right labels, it may do so for the wrong reasons. Diffuse feature combinations may vary across classifier families and lack a dominant feature. This paper proposes FLEX (Fisher LDA Explainer), a global surrogate that fits a single direct multi-label Fisher LDA over the full binary label matrix, producing signed feature attribution lists for each label in a single coherent coordinate system. Across the evaluated benchmarks and classifier families, FLEX reproduces the black box's predictions with consistently high fidelity. Pooling covariance across labels outperforms a per-label alternative on most datasets, with the advantage growing largest where labels are numerous and positive examples are scarce. FLEX's fidelity-complexity Pareto curve is monotonically increasing, giving practitioners a predictable path to higher-fidelity explanations as more features are used, and its in-sample fidelity matches or leads Binary Relevance alternatives once a modest feature budget is allowed. The magnitude of each discriminant weight vector bounds its label's separability, flagging labels that may be predicted correctly for the wrong reasons. The evaluated classifiers largely agree on which predictions to make, but reach those decisions through different feature subsets when no single feature dominates.

Figures & tables

Explore similar work

CardsList
  1. Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations

    May 20, 2026Jacek Karolczak, Jerzy StefanowskiPrototype-Based ClassificationPrototype-Based Explanation