arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12679cs.LGstat.ML
收藏

变分选择性自动编码器:从部分观察的异构数据中学习

Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data

Borealis AI(博雷尔AI);Simon Fraser University(西蒙菲莎大学)

Yu Gong, Hossein Hajimirsadeghi, Jiawei He, Thibaut Durand, Greg Mori

摘要:

从异构数据中学习带来了挑战,例如组合来自不同来源和不同类型的数据。同时,在实际应用中,由于输入源的异构性和噪声,异构数据往往伴随着丢失。在这项工作中,我们提出了变分选择性自动编码器(VSAE),一个通用的框架来学习表示部分观察到的异构数据。VSAE通过对观测数据、未观测数据和表示数据如何丢失的插补掩码的联合分布进行建模,来学习异构数据中的潜在依赖关系。它为包括数据生成和估算在内的各种下游任务提供了一个统一的模型。对这两个任务的低维和高维异构数据集的评估显示了对最先进模型的改进。

英文摘要:

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and noise of input sources. In this work, we propose the variational selective autoencoder (VSAE), a general framework to learn representations from partially-observed heterogeneous data. VSAE learns the latent dependencies in heterogeneous data by modeling the joint distribution of observed data, unobserved data, and the imputation mask which represents how the data are missing. It results in a unified model for various downstream tasks including data generation and imputation. Evaluation on both low-dimensional and high-dimensional heterogeneous datasets for these two tasks shows improvement over state-of-the-art models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑