Forward Composition Propagation for Explainable Neural Reasoning

Isel Grau, Gonzalo Nápoles, Marilyn Bello, Yamisleydi Salgueiro, Agnieszka Jastrzebska

    Research output: Contribution to journalArticleScientificpeer-review

    28 Downloads (Pure)

    Abstract

    This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently propagated through the whole network until reaching the output layer. The sign of each composition value indicates whether the corresponding feature excites or inhibits the neuron, while the absolute value quantifies its impact. The FCP algorithm is executed on a post-hoc basis, i.e., once the learning process is completed. Aiming to illustrate the FCP algorithm, this paper develops a case study concerning bias detection in a fairness problem in which the ground truth is known. The simulation results show that the composition values closely align with the expected behavior of protected features. The source code and supplementary material for this paper are available at https://github.com/igraugar/fcp.
    Original languageEnglish
    Pages (from-to)26-35
    Number of pages10
    JournalIEEE Computational Intelligence Magazine
    Volume19
    Issue number1
    DOIs
    Publication statusPublished - 26 Oct 2022

    Keywords

    • cs.LG
    • cs.AI

    Fingerprint

    Dive into the research topics of 'Forward Composition Propagation for Explainable Neural Reasoning'. Together they form a unique fingerprint.

    Cite this