论文标题

使用对抗性自动编码器统一的多域学习和数据插补

Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder

论文作者

Mendes, Andre, Togelius, Julian, Coelho, Leandro dos Santos

论文摘要

我们提出了一个新颖的框架,可以结合多域学习(MDL),数据插补(DI)和多任务学习(MTL),以提高不同域中分类和回归任务的性能。我们方法的核心是一种对抗性自动编码器,可以:(1)学会产生域不变的嵌入以减少域之间的差异; (2)了解每个域的数据分布,并在丢失的数据上正确执行数据插补。对于MDL,我们使用最大平均差异(MMD)度量来对齐域分布。对于DI,我们使用一种对抗方法,其中发电机填充缺少数据的信息,并且歧视器试图区分实际值和估算值。最后,使用嵌入式中的通用特征表示形式,我们使用MTL训练分类器,该分类器可以从任何域中给出输入,可以预测所有域的标签。我们证明了与其他三种不同的设置中的其他最新方法相比,我们的方法的出色性能,图像识别中具有非结构化数据的DG-DI,在级别估计中使用结构化数据进行MTL-DI和使用混合数据的选择过程中的MDMTL-DI。

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data. For MDL, we use the Maximum Mean Discrepancy (MMD) measure to align the domain distributions. For DI, we use an adversarial approach where a generator fill in information for missing data and a discriminator tries to distinguish between real and imputed values. Finally, using the universal feature representation in the embeddings, we train a classifier using MTL that given input from any domain, can predict labels for all domains. We demonstrate the superior performance of our approach compared to other state-of-art methods in three distinct settings, DG-DI in image recognition with unstructured data, MTL-DI in grade estimation with structured data and MDMTL-DI in a selection process using mixed data.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源