mlsanityData to 7 Oct 2026

CauScale: Neural Causal Discovery at Scale

arXiv 2602.08629 ↗First posted 9 Feb 2026cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500-node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data, while delivering 4-13,000 times inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 39 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

16 of 39 references.

References · 16

  1. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  2. 2019Gradient-Based Neural DAG Learningcited by 227
  3. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  4. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 165
  5. 2019Causal Discovery with Reinforcement Learningcited by 145
  6. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  7. 2022Amortized Inference for Causal Structure Learningcited by 89
  8. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  9. 2022Learning to Induce Causal Structurecited by 68
  10. 2022Diffusion Models for Causal Discovery via Topological Orderingcited by 64
  11. 2023Stable Differentiable Causal Discoverycited by 30
  12. 2017Causal Generative Neural Networkscited by 24
4 more
  1. 2024A Meta-Learning Approach to Bayesian Causal Discoverycited by 22
  2. 2024Sample, estimate, aggregate: A recipe for causal discovery foundation modelscited by 19
  3. 2024Adjustment Identification Distance: A gadjid for Causal Structure Learningcited by 16
  4. 2025Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Seriescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Arrow: A Foundation Model for Causal Discoverycited by 4
  2. 2026CDFM: Towards a General-Purpose Causal Discovery Foundation Modelcited by 2
  3. 2026DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanismscited by 2
  4. 2026CauTion: Knowing When to Trust LLMs for Ensemble Causal Discoverycited by 1
  5. 2026CausalArena: Benchmarking Causal Discovery in the Foundation Model Eracited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CauSight: Learning to Supersense for Visual Causal Discovery
  2. 2026CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
  3. 2026TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
  4. 2026Optimizing Graph Causal Classification Models: Estimating Causal Effects and Addressing Confounders
  5. 2025Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem
  6. 2023CUTS+: High-dimensional Causal Discovery from Irregular Time-series
  7. 2026Latent Confounded Causal Discovery via Lie Bracket Geometry
  8. 2026CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts