Causal Discovery with Attention-Based Convolutional Neural Networks

By Meike Nauta, Doina Bucur, Christin Seifert. Machine Learning and Knowledge Extraction, 2019

346 citations recorded by the source corpus.

Having insight into the causal associations in a complex system facilitates decision making, e.g., for medical treatments, urban infrastructure improvements or financial investments. The amount of observational data grows, which enables the discovery of causal relationships between variables from observation of their behaviour in time. Existing methods for causal discovery from time series data do not yet exploit the representational power of deep learning. We therefore present the Temporal Causal Discovery Framework (TCDF), a deep learning framework that learns a causal graph structure by discovering causal relationships in observational time series data. TCDF uses attention-based convolutional neural networks combined with a causal validation step. By interpreting the internal parameters of the convolutional networks, TCDF can also discover the time delay between a cause and the occurrence of its effect. Our framework learns temporal causal graphs, which can include confounders and instantaneous effects. Experiments on financial and neuroscientific benchmarks show state-of-the-art performance of TCDF on discovering causal relationships in continuous time series data. Furthermore, we show that TCDF can circumstantially discover the presence of hidden confounders. Our broadly applicable framework can be used to gain novel insights into the causal dependencies in a complex system, which is important for reliable predictions, knowledge discovery and data-driven decision making.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/0acde5caee011535b2e98c3b12b4f29d4e7e461c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Silvio Savarese
2. Li Fei-Fei
3. Yuke Zhu
4. Suraj Nair
5. Abhinav Kumar Gupta
6. Chenhao Tan
7. Sergey Levine
8. Trevor Darrell

In Management Science and Operations Research

1. Silvio Savarese
2. Yuke Zhu
3. Emre Kıcıman
4. Chenhao Tan
5. Li Fei-Fei

Citations in the corpus

• Deep Learning for Medical Anomaly Detection – A Survey (2020, neutral): “Existing approaches for causality estimation in deep learning studies include causal graph structures [95], algorithmic information theory–based approaches [145, 146], and Causal Bayesian Networks [99, 150]; however, these methods are seldom applied in medical abnormality detection.”
• Causal Reasoning and Large Language Models: Opening a New Frontier for Causality (2023, background): “…is low (12), we are able to conduct an experiment to discover the full graph using LLMs. Huang et al. (2021) evaluate the accuracy of three recent discovery algorithms: temporal causality discovery framework (Nauta et al., 2019), NOTEARS (Zheng et al., 2018), and DAG-GNN (Yu et al., 2019).”
• Causal Induction from Visual Observations for Goal Directed Tasks (2019, background): “Pioneer work on causal discovery with deep networks has applied to time series data in healthcare domains (Kale et al., 2015; Nauta et al., 2019).”