Demystifying amortized causal discovery with transformers

• URL: http://arxiv.org/abs/2405.16924v1
• Date: Mon, 27 May 2024 08:17:49 GMT
• Title: Demystifying amortized causal discovery with transformers
• Authors: Francesco Montagna, Max Cairney-Leeming, Dhanya Sridhar, Francesco Locatello,
• Abstract summary: Supervised learning approaches for causal discovery from observational data often achieve competitive performance. In this work, we investigate CSIvA, a transformer-based model promising to train on synthetic data and transfer to real data. We bridge the gap with existing identifiability theory and show that constraints on the training data distribution implicitly define a prior on the test observations.
• Score: 21.058343547918053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Supervised learning approaches for causal discovery from observational data often achieve competitive performance despite seemingly avoiding explicit assumptions that traditional methods make for identifiability. In this work, we investigate CSIvA (Ke et al., 2023), a transformer-based model promising to train on synthetic data and transfer to real data. First, we bridge the gap with existing identifiability theory and show that constraints on the training data distribution implicitly define a prior on the test observations. Consistent with classical approaches, good performance is achieved when we have a good prior on the test data, and the underlying model is identifiable. At the same time, we find new trade-offs. Training on datasets generated from different classes of causal models, unambiguously identifiable in isolation, improves the test generalization. Performance is still guaranteed, as the ambiguous cases resulting from the mixture of identifiable causal models are unlikely to occur (which we formally prove). Overall, our study finds that amortized causal discovery still needs to obey identifiability theory, but it also differs from classical methods in how the assumptions are formulated, trading more reliance on assumptions on the noise type for fewer hypotheses on the mechanisms.

Related papers

• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Sample, estimate, aggregate: A recipe for causal discovery foundation models [28.116832159265964]
  We train a supervised model that learns to predict a larger causal graph from the outputs of classical causal discovery algorithms run over subsets of variables. Our approach is enabled by the observation that typical errors in the outputs of classical methods remain comparable across datasets. Experiments on real and synthetic data demonstrate that this model maintains high accuracy in the face of misspecification or distribution shift.
  arXiv  Detail & Related papers  (2024-02-02T21:57:58Z)
• Identifiable Latent Polynomial Causal Models Through the Lens of Change [82.14087963690561]
  Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
  arXiv  Detail & Related papers  (2023-10-24T07:46:10Z)
• Discovering Mixtures of Structural Causal Models from Time Series Data [23.18511951330646]
  We propose a general variational inference-based framework called MCD to infer the underlying causal models. Our approach employs an end-to-end training process that maximizes an evidence-lower bound for the data likelihood. We demonstrate that our method surpasses state-of-the-art benchmarks in causal discovery tasks.
  arXiv  Detail & Related papers  (2023-10-10T05:13:10Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Testing for Overfitting [0.0]
  We discuss the overfitting problem and explain why standard and concentration results do not hold for evaluation with training data. We introduce and argue for a hypothesis test by means of which both model performance may be evaluated using training data.
  arXiv  Detail & Related papers  (2023-05-09T22:49:55Z)
• Hypothesis Testing using Causal and Causal Variational Generative Models [0.0]
  Causal Gen and Causal Variational Gen can utilize nonparametric structural causal knowledge combined with a deep learning functional approximation. We show how, using a deliberate (non-random) split of training and testing data, these models can generalize better to similar, but out-of-distribution data points. We validate our methods on a synthetic pendulum dataset, as well as a trauma surgery ground level fall dataset.
  arXiv  Detail & Related papers  (2022-10-20T13:46:15Z)
• Amortized Inference for Causal Structure Learning [72.84105256353801]
  Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test. We train a variational inference model to predict the causal structure from observational/interventional data. Our models exhibit robust generalization capabilities under substantial distribution shift.
  arXiv  Detail & Related papers  (2022-05-25T17:37:08Z)
• Typing assumptions improve identification in causal discovery [123.06886784834471]
  Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. We propose a new set of assumptions that constrain possible causal relationships based on the nature of the variables.
  arXiv  Detail & Related papers  (2021-07-22T14:23:08Z)
• Testing for Typicality with Respect to an Ensemble of Learned Distributions [5.850572971372637]
  One-sample approaches to the goodness-of-fit problem offer significant computational advantages for online testing. The ability to correctly reject anomalous data in this setting hinges on the accuracy of the model of the base distribution. Existing methods for the one-sample goodness-of-fit problem do not account for the fact that a model of the base distribution is learned. We propose training an ensemble of density models, considering data to be anomalous if the data is anomalous with respect to any member of the ensemble.
  arXiv  Detail & Related papers  (2020-11-11T19:47:46Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.