Ensembles-based Feature Guided Analysis

TL;DR

This paper introduces EFGA, an ensemble-based extension of FGA, which improves the recall of rule-based explanations in DNNs with minimal impact on precision, tested on MNIST and LSC datasets.

Contribution

EFGA combines rules into ensembles with different criteria, enhancing explanation applicability while maintaining high precision, advancing interpretability of deep neural networks.

Findings

EFGA increases recall significantly on MNIST and LSC datasets.

Different ensemble criteria balance precision and recall trade-offs.

EFGA outperforms FGA in recall with negligible precision loss.

Abstract

Recent Deep Neural Networks (DNN) applications ask for techniques that can explain their behavior. Existing solutions, such as Feature Guided Analysis (FGA), extract rules on their internal behaviors, e.g., by providing explanations related to neurons activation. Results from the literature show that these rules have considerable precision (i.e., they correctly predict certain classes of features), but the recall (i.e., the number of situations these rule apply) is more limited. To mitigate this problem, this paper presents Ensembles-based Feature Guided Analysis (EFGA). EFGA combines rules extracted by FGA into ensembles. Ensembles aggregate different rules to increase their applicability depending on an aggregation criterion, a policy that dictates how to combine rules into ensembles. Although our solution is extensible, and different aggregation criteria can be developed by users, in this work, we considered three different aggregation criteria. We evaluated how the choice of the criterion influences the effectiveness of EFGA on two benchmarks (i.e., the MNIST and LSC datasets), and found that different aggregation criteria offer alternative trade-offs between precision and recall. We then compare EFGA with FGA. For this experiment, we selected an aggregation criterion that provides a reasonable trade-off between precision and recall. Our results show that EFGA has higher train recall (+28.51% on MNIST, +33.15% on LSC), and test recall (+25.76% on MNIST, +30.81% on LSC) than FGA, with a negligible reduction on the test precision (-0.89% on MNIST, -0.69% on LSC).