Pith. sign in

REVIEW 5 cited by

DAG-GNN: DAG Structure Learning with Graph 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

arxiv 1904.10098 v1 pith:TIMN6WSI submitted 2019-04-22 cs.LG cs.AIstat.ML

DAG-GNN: DAG Structure Learning with Graph Neural Networks

classification cs.LG cs.AIstat.ML
keywords graphmodeldag-gnnlearningstructuralapplyconstraintdata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes. A recent breakthrough formulates the problem as a continuous optimization with a structural constraint that ensures acyclicity (Zheng et al., 2018). The authors apply the approach to the linear structural equation model (SEM) and the least-squares loss function that are statistically well justified but nevertheless limited. Motivated by the widespread success of deep learning that is capable of capturing complex nonlinear mappings, in this work we propose a deep generative model and apply a variant of the structural constraint to learn the DAG. At the heart of the generative model is a variational autoencoder parameterized by a novel graph neural network architecture, which we coin DAG-GNN. In addition to the richer capacity, an advantage of the proposed model is that it naturally handles discrete variables as well as vector-valued ones. We demonstrate that on synthetic data sets, the proposed method learns more accurate graphs for nonlinearly generated samples; and on benchmark data sets with discrete variables, the learned graphs are reasonably close to the global optima. The code is available at \url{https://github.com/fishmoon1234/DAG-GNN}.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI

    eess.IV 2026-06 unverdicted novelty 7.0

    A framework generates synthetic neuroimages with explicit causal control via volumetric ROI changes to produce ground-truth data for benchmarking causal AI in neuroimaging.

  2. Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis

    eess.SP 2026-05 unverdicted novelty 6.0

    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.

  3. Visual Analysis of Multi-outcome Causal Graphs

    cs.LG 2024-07 unverdicted novelty 6.0

    Introduces progressive visualization for comparing causal discovery algorithms and comparative graph layouts for analyzing multi-outcome causal graphs in healthcare.

  4. Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection

    cs.AI 2026-06 unverdicted novelty 5.0

    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.

  5. Proactive Dialogue Model with Intent Prediction

    cs.CL 2026-04 unverdicted novelty 5.0

    A Temporal Bayesian Network derived from MultiWOZ intent annotations predicts user intent transitions and guides proactive dialogue generation, raising Coverage AUC from 0.742 to 0.856 while cutting turns to 75% cover...