Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from temporal sequences of observations under the assumption that there are no instantaneous causal relations between them. In practical applications, however, our measurement or frame rate might be slower than many of the causal effects. This effectively creates "instantaneous" effects and invalidates previous identifiability results. To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e.g., as actions of an agent. iCITRIS identifies the potentially multidimensional causal variables from temporal observations, while simultaneously using a differentiable causal discovery method to learn their causal graph. In experiments on three datasets of interactive systems, iCITRIS accurately identifies the causal variables and their causal graph.
翻译:近期的工作表明,我们可以根据时间序列观测来重建因果变量,假设它们之间没有即时因果关系。然而,在实际应用中,我们的计量或框架率可能比许多因果效果慢。这实际上造成了“即时”效应,使先前的可识别性结果失效。为了解决这一问题,我们提议了iCITRIS, 这是一种因果学习方法,允许在能够观察到干预目标时即时在干预时间序列中发生即时效果,例如,当一个代理人的行动时,iCITRIS从时间观察中找出潜在的多层面因果变量,同时使用不同的因果发现方法了解其因果图时。在对互动系统的三个数据集的实验中,iCITRIS准确地确定了因果变量及其因果图表。</s>