REVIEW 4 cited by
Causal Generative Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs leverage conditional independencies and distributional asymmetries to discover bivariate and multivariate causal structures. CGNNs make no assumption regarding the lack of confounders, and learn a differentiable generative model of the data by using backpropagation. Extensive experiments show their good performances comparatively to the state of the art in observational causal discovery on both simulated and real data, with respect to cause-effect inference, v-structure identification, and multivariate causal discovery.
Forward citations
Cited by 4 Pith papers
-
Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis
Pilot study uses pretrained video encoder features from lung ultrasound to predict 30-day CHF readmission, finding lower-lung views and temporal differences most informative with top MLP F1 of 0.80.
-
Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection
Empirical evaluation on synthetic and real-world datasets indicates that natural experiments are present and can be leveraged via causal feature selection to boost model performance.
-
CauScale: Neural Causal Discovery at Scale
CauScale uses a two-stream neural architecture with a sample-reduction unit and tied attention weights to scale amortized causal discovery to 1000-node graphs.
-
Large Causal Models for Temporal Causal Discovery
A transformer pretrained on a large mixed corpus of synthetic and simulated realistic time series can discover lagged causal graphs zero-shot on datasets up to 12 variables, outperforming several classical baselines.
Discussion (0). Continue with ORCID to comment.