mlsanityData to 14 Oct 2026

A Knowledge-Informed Pretrained Model for Causal Discovery

arXiv 2603.20842 ↗First posted 21 Mar 2026cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data driven paradigms with limited guidance, which hinders practical deployment. Motivated by real-world scenarios where only coarse domain knowledge is available, we propose a knowledge-informed pretrained model for causal discovery that integrates weak prior knowledge as a principled middle ground. Our model adopts a dual source encoder-decoder architecture to process observational data in a knowledge-informed way. We design a diverse pretraining dataset and a curriculum learning strategy that smoothly adapts the model to varying prior strengths across mechanisms, graph densities, and variable scales. Extensive experiments on in-distribution, out-of distribution, and real-world datasets demonstrate consistent improvements over existing baselines, with strong robustness and practical applicability.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

18 of 31 references.

References · 18

  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  3. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  4. 2019Gradient-Based Neural DAG Learningcited by 227
  5. 2019Learning Sparse Nonparametric DAGscited by 207
  6. 2018Learning Latent Permutations with Gumbel-Sinkhorn Networkscited by 175
  7. 2021Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Gamecited by 161
  8. 2019Causal Discovery with Reinforcement Learningcited by 145
  9. 2022The Devil in Linear Transformercited by 98
  10. 2022Amortized Inference for Causal Structure Learningcited by 90
  11. 2022Learning to Induce Causal Structurecited by 68
  12. 2019A Graph Autoencoder Approach to Causal Structure Learningcited by 55
6 more
  1. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  2. 2022Differentiable DAG Samplingcited by 47
  3. 2021NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledgecited by 33
  4. 2025CausalRivers -- Scaling up benchmarking of causal discovery for real-world time-seriescited by 26
  5. 2024A Meta-Learning Approach to Bayesian Causal Discoverycited by 22
  6. 2022CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methodscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Arrow: A Foundation Model for Causal Discoverycited by 5
  2. 2026Demistifying Data and Simulator Assumptions in Supervised Causal Discoverycited by 0