通过属性对齐实现医学声音诊断的可解释表征学习
Disentangling Representation using Attributes-based Gaussian Estimation for Medical Sound Diagnosis
- 用属性嵌入模块将医学特征映射到变分自编码器的潜在向量
- 最小化互信息使关键属性表征与其它特征解耦，准确率达89.6%
- 提升模型公平性与可解释性，适合医疗场景的可信AI研发
深度学习具备强大的特征提取能力，但其在医疗领域中的应用受限于缺乏公平性和可解释性。本文提出一种名为基于属性的高斯估计解耦表征（AGEDR）的解耦表征学习框架，引入属性映射嵌入（AME）模块，将属性映射为向量并对其齐变分自编码器（VAE）中部分潜在向量。通过最小化互信息，使该部分潜在向量从其余向量中解耦。随后使用VAE潜在向量的均值参数训练分类器。大量实验表明，AGEDR在性能上超越传统分类模型及现有解耦学习方法，消融实验验证了其解耦能力和公平性。代码已公开于https://github.com/ZhaoKe1024/DisentangledRepr。
原文摘要 · Abstract (English)
Deep learning has a powerful capability of feature extraction. However, the lack of fairness and interpretability in deep neural networks poses limitations to their adoption in the medical domain. This paper proposes a disentangled representation learning (DisenRL) framework, named the Attributes-based Gaussian Estimation for Disentangled Representation (AGEDR), which incorporates Attribute Mapping Embedding (AME) modules designed to map attributes into vectors and align them with a subset of the latent vectors in a Variational AutoEncoder (VAE). This part of the latent vector will be disentangled from the remaining latent vectors by minimizing mutual information. A classifier is then trained using the mean parameters of the latent vectors from the VAE. Extensive experiments demonstrate that AGEDR outperforms both conventional classification models and existing disentangled representation learning methods. The ablation experiments also indicate the disentangling capability and fairness of AGEDR. The source code is publicly available at https://github.com/ZhaoKe1024/DisentangledRepr.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。