GAMI-Net: An explainable neural network based on generalized additive models with structured interactions
作者：
Highlights：
• A novel explainable neural network is proposed for modeling main effects and structured interactions.
• The GAMI-Net is a disentangled feedforward network with multiple additive subnetworks.
• GAMI-Net takes into account three interpretability constraints: sparsity, heredity, marginal clarity.
• An adaptive training algorithm is developed for training GAMI-Net efficiently.
• GAMI-Net enjoys superior interpretability and outperforms benchmark methods.
摘要
•A novel explainable neural network is proposed for modeling main effects and structured interactions.•The GAMI-Net is a disentangled feedforward network with multiple additive subnetworks.•GAMI-Net takes into account three interpretability constraints: sparsity, heredity, marginal clarity.•An adaptive training algorithm is developed for training GAMI-Net efficiently.•GAMI-Net enjoys superior interpretability and outperforms benchmark methods.
论文关键词：Explainable neural network,Generalized additive model,Pairwise interaction,Interpretability constraints
论文评审过程：Received 4 November 2020, Revised 28 June 2021, Accepted 4 July 2021, Available online 20 July 2021, Version of Record 28 July 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108192
