Neural Processes (NPs) consider a task as a function realized from a stochastic process and flexibly adapt to unseen tasks through inference on functions. However, naive NPs can model data from only a single stochastic process and are designed to infer each task independently. Since many real-world data represent a set of correlated tasks from multiple sources (e.g., multiple attributes and multi-sensor data), it is beneficial to infer them jointly and exploit the underlying correlation to improve the predictive performance. To this end, we propose Multi-Task Processes (MTPs), an extension of NPs designed to jointly infer tasks realized from multiple stochastic processes. We build our MTPs in a hierarchical manner such that inter-task correlation is considered by conditioning all per-task latent variables on a single global latent variable. In addition, we further design our MTPs so that they can address multi-task settings with incomplete data (i.e., not all tasks share the same set of input points), which has high practical demands in various applications. Experiments demonstrate that MTPs can successfully model multiple tasks jointly by discovering and exploiting their correlations in various real-world data such as time series of weather attributes and pixel-aligned visual modalities.
翻译:神经过程( NPs) 将任务视为从随机进程中实现的函数, 并通过函数的推断灵活地适应不可见的任务。 然而, 天真的 NPs 只能从单一的随机过程模拟数据, 并且设计可以独立地推断每项任务。 由于许多真实世界数据代表着来自多个来源的一组相关任务( 如多重属性和多传感器数据), 因此, 联合推断它们并利用基本关联来改进预测性能是有益的。 为此, 我们提议多任务进程( MTPs ), 用于联合推导从多个随机过程完成的任务的NPs 扩展。 我们以等级化的方式构建我们的MTPs, 这样, 通过将每个任务的潜在变量都调整到一个单一的全球潜在变量上来考虑跨任务。 此外, 我们进一步设计我们的MTPs, 以便它们能够用不完整的数据( 即并非所有任务都共享相同的输入点) 来应对多任务设置。 多任务, 这在各种应用中都具有高度的实际需求。 我们用一个层次的方式构建我们的 MTPsalimal- diralimalimal- das exignalignalignal ex ex