论文标题
Autobayes：自动化贝叶斯图探索，用于刺激性推理
AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference
论文作者
论文摘要
学习捕获与任务相关的功能但对令人讨厌的变化不变的数据表示是机器学习的关键挑战。我们介绍了一个称为AutoBayes的自动化贝叶斯推理框架，该框架探索了链接分类器，编码器，解码器，估算器和对抗网络块的不同图形模型，以优化令人讨厌的不变的机器学习管道。 AutoBayes还可以实现学习分离的表示，其中潜在变量分为多个部分，以与滋扰变化和任务标签施加各种关系。我们在几个公共数据集上进行基准测试框架，并在具有/没有各种建模和对抗性培训的情况下分析其对主题转移学习的能力。通过探索图形模型，我们通过集合学习表现出显着的性能提高。
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores different graphical models linking classifier, encoder, decoder, estimator and adversarial network blocks to optimize nuisance-invariant machine learning pipelines. AutoBayes also enables learning disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels. We benchmark the framework on several public datasets, and provide analysis of its capability for subject-transfer learning with/without variational modeling and adversarial training. We demonstrate a significant performance improvement with ensemble learning across explored graphical models.
