Causal conditional hidden Markov model for multimodal traffic prediction
This work addresses urban traffic management by improving prediction accuracy through causal modeling, but it appears incremental as it builds on existing hidden Markov models with causal enhancements.
The paper tackles the problem of multimodal traffic flow prediction by addressing the overemphasis on spatio-temporal correlations and ignoring causal relationships, proposing a Causal Conditional Hidden Markov Model (CCHMM) that effectively disentangles causal representations and accurately predicts traffic flow, as shown in experiments on real-world datasets.
Multimodal traffic flow can reflect the health of the transportation system, and its prediction is crucial to urban traffic management. Recent works overemphasize spatio-temporal correlations of traffic flow, ignoring the physical concepts that lead to the generation of observations and their causal relationship. Spatio-temporal correlations are considered unstable under the influence of different conditions, and spurious correlations may exist in observations. In this paper, we analyze the physical concepts affecting the generation of multimode traffic flow from the perspective of the observation generation principle and propose a Causal Conditional Hidden Markov Model (CCHMM) to predict multimodal traffic flow. In the latent variables inference stage, a posterior network disentangles the causal representations of the concepts of interest from conditional information and observations, and a causal propagation module mines their causal relationship. In the data generation stage, a prior network samples the causal latent variables from the prior distribution and feeds them into the generator to generate multimodal traffic flow. We use a mutually supervised training method for the prior and posterior to enhance the identifiability of the model. Experiments on real-world datasets show that CCHMM can effectively disentangle causal representations of concepts of interest and identify causality, and accurately predict multimodal traffic flow.