Loading...
Causal Temporal Representation Learning with Nonstationary Sparse Transition
Song, Xiangchen Li, Zijian Chen, Guangyi Zheng, Yujia Fan, Yewen Dong, Xinshuai Zhang, Kun
Song, Xiangchen
Li, Zijian
Chen, Guangyi
Zheng, Yujia
Fan, Yewen
Dong, Xinshuai
Zhang, Kun
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctrl methods, they require either directly observing the domain variables or assuming a Markov prior on them. Such requirements limit the application of these methods in real-world scenarios when we do not have such prior knowledge of the domain variables. To address this problem, this work adopts a sparse transition assumption, aligned with intuitive human understanding, and presents identifiability results from a theoretical perspective. In particular, we explore under what conditions on the significance of the variability of the transitions we can build a model to identify the distribution shifts. Based on the theoretical result, we introduce a novel framework, Causal Temporal Representation Learning with Nonstationary Sparse Transition (CtrlNS), designed to leverage the constraints on transition sparsity and conditional independence to reliably identify both distribution shifts and latent factors. Our experimental evaluations on synthetic and real-world datasets demonstrate significant improvements over existing baselines, highlighting the effectiveness of our approach.
Citation
X. Song et al., “Causal Temporal Representation Learning with Nonstationary Sparse Transition,” Adv Neural Inf Process Syst, vol. 37, pp. 77098–77131, Dec. 2024.
Source
Advances in Neural Information Processing Systems (NeurIPS 2024)
Conference
Keywords
Causal Temporal Representation Learning (Ctrl), Nonstationary sparse transitions, Latent variable identification, Distribution shifts, Variational Autoencoder (VAE) framework
Subjects
Source
Publisher
NEURIPS