Causal Generative Neural Networks
By Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle M Guyon, David Lopez-Paz, Michèle Sebag. 2017
69 citations recorded by the source corpus.
We introduce CGNN, a framework to learn functional causal models as generative neural networks. These networks are trained using backpropagation to minimize the maximum mean discrepancy to the observed data. Unlike previous approaches, CGNN leverages both conditional independences and distributional asymmetries to seamlessly discover bivariate and multivariate causal structures, with or without hidden variables. CGNN does not only estimate the causal structure, but a full and differentiable generative model of the data. Throughout an extensive variety of experiments, we illustrate the competitive esults of CGNN w.r.t state-of-the-art alternatives in observational causal discovery on both simulated and real data, in the tasks of cause-effect inference, v-structure identification, and multivariate causal discovery.
Subfields: Artificial Intelligence, Generative Models, Causal Inference & Discovery
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
- Yoshua Bengio
- Bernhard Schölkopf
- Anirudh Goyal
- Quoc V. Le
- Kyunghyun Cho
- Sergey Levine
- Mohit Bansal
- Dacheng Tao
In Generative Models
- Yoshua Bengio
- Stefano Ermon
- Anirudh Goyal
- Yang Song
- Aaron C. Courville
- Bernhard Schölkopf
- Nal Kalchbrenner
- Nan Rosemary Ke
In Causal Inference & Discovery
- Yoshua Bengio
- Anirudh Goyal
- Bernhard Schölkopf
- David Lopez-Paz
- Stefan Bauer
- Francesco Locatello
- Nan Rosemary Ke
- Isabelle M Guyon
Citations in the corpus
- Towards Causal Representation Learning (2021, background): “[237, 188, 229, 113, 174, 187, 139, 17, 246, 277, 175, 123, 186, 176, 36, 82, 161], learning causal relations frequently requires collecting data from multiple environments, or the ability to perform interventions [251].”
- Causality for Machine Learning (2019, background): “al question. Our opinions have since then converged, and research has started to appear that combines both fields (Bengio et al., 2019; Goyal et al., 2019; Locatello et al., 2018a; Suter et al., 2018; Goudet et al., 2017). All this is still in its infancy, and the above account is personal and thus b”
- Learning Neural Causal Models from Unknown Interventions (2019, background): “A lot of prior work has examined learning causal structure based on observational data (Chickering, 2002; Tsamardinos et al., 2006; Goudet et al., 2017; Hauser & Bühlmann, 2012; Spirtes et al., 2000; Sun et al., 2007; Zhang et al., 2012; Shimizu et al., 2006; Hoyer et al., 2009; Daniusis et al.,…”
- SAM: Structural Agnostic Model, Causal Discovery and Penalized Adversarial Learning (2018, methodology): “Both CAM and CGNN leverage conditional independences and distributional asymmetries for multivariate causal discovery.”