Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we are observing. While many models have been introduced to learn such disentangled representations, only few attempt to explicitly exploit the structure of sequential data. We investigate the disentanglement properties of Gaussian process variational autoencoders, a class of models recently introduced that have been successful in different tasks on time series data. Our model exploits the temporal structure of the data by modeling each latent channel with a GP prior and employing a structured variational distribution that can capture dependencies in time. We demonstrate the competitiveness of our approach against state-of-the-art unsupervised and weakly-supervised disentanglement methods on a benchmark task. Moreover, we provide evidence that we can learn meaningful disentangled representations on real-world medical time series data.
翻译:从计算机视觉到机器人或医学等许多领域都会出现复杂的多变时间序列。 我们通常对产生我们所观测的高维数据的独立基本因素感兴趣。 虽然许多模型被引入来学习这种分解的表达方式,但很少有人试图明确利用相继数据的结构。 我们调查了高西亚过程的分解特性,这是最近推出的一组模型,在时间序列数据的不同任务中取得了成功。 我们的模型利用了数据的时间结构,先用GP模型对每个潜在渠道进行模拟,然后采用结构化的变异分布,从而能够及时捕捉到依赖性。 我们展示了我们的方法在基准任务上对抗最先进的、不受监督和监管的不协调的分解方法的竞争力。 此外,我们提供了证据,我们可以了解真实世界医疗时间序列数据中有意义的分解的表达方式。