mlsanityData to 14 Oct 2026

polyDAG: Polynomial Acyclicity Constraints for Efficient Continuous Causal Discovery in Visual Semantic Graphs

arXiv 2606.06908 ↗First posted 5 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern image-analysis pipelines often convert images into structured semantic variables, such as facial attributes, object concepts, and scene descriptors. Learning directed dependencies among these variables can produce interpretable visual semantic graphs, but continuous directed acyclic graph learning is limited by the cost of enforcing acyclicity. We present polyDAG, a polynomial acyclicity framework for efficient continuous causal discovery in visual semantic graphs. polyDAG replaces the matrix-exponential acyclicity constraint with a finite polynomial trace constraint and proves that the new constraint is zero exactly for acyclic graphs. We further derive a geometric-series implementation that avoids the explicit summation loop while preserving the same acyclicity condition. Experiments on synthetic Erdos-Renyi graphs and CelebA facial visual attributes show that polyDAG improves efficiency and structure recovery. Averaged over the revised synthetic protocol with d in {100, 200, 500}, polyDAG reduces mean structural Hamming distance from 318.4 to 285.4 and improves mean F1 score from 0.725 to 0.756. At 100 nodes, the geometric variant runs in 3.44 seconds compared with 5.16 seconds for the exponential baseline, corresponding to a 33.4 percent speedup. Code and data are publicly available at https://github.com/wenhaoz-fengcai/polyDAG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 60 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

23 of 60 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2021Convex optimizationcited by 2,515
  5. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  6. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  7. 2019Gradient-Based Neural DAG Learningcited by 227
  8. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  9. 2019Causality matters in medical imagingcited by 193
  10. 2020On the Role of Sparsity and DAG Constraints for Learning Linear DAGscited by 191
  11. 2019Causal Discovery with Reinforcement Learningcited by 145
  12. 2022DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterizationcited by 140
11 more
  1. 2021Causal Attention for Vision-Language Taskscited by 111
  2. 2021DiBS: Differentiable Bayesian Structure Learningcited by 106
  3. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  4. 2021BCD Nets: Scalable Variational Approaches for Bayesian Causal Discoverycited by 68
  5. 2018Structural Agnostic Modeling: Adversarial Learning of Causal Graphscited by 48
  6. 2022Differentiable DAG Samplingcited by 47
  7. 2022Large-Scale Differentiable Causal Discovery of Factor Graphscited by 47
  8. 2015A fast PC algorithm for high dimensional causal discovery with multi-core PCscited by 45
  9. 2018Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Datacited by 39
  10. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  11. 2024Reinforcement Learning for Causal Discovery without Acyclicity Constraintscited by 3

Built on by

Not cited yet.