mlsanityData to 7 Oct 2026

CausalBench: A Large-scale Benchmark for Network Inference from Single-cell Perturbation Data

arXiv 2210.17283 ↗First posted 31 Oct 2022cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

Causal inference is a vital aspect of multiple scientific disciplines and is routinely applied to high-impact applications such as medicine. However, evaluating the performance of causal inference methods in real-world environments is challenging due to the need for observations under both interventional and control conditions. Traditional evaluations conducted on synthetic datasets do not reflect the performance in real-world systems. To address this, we introduce CausalBench, a benchmark suite for evaluating network inference methods on real-world interventional data from large-scale single-cell perturbation experiments. CausalBench incorporates biologically-motivated performance metrics, including new distribution-based interventional metrics. A systematic evaluation of state-of-the-art causal inference methods using our CausalBench suite highlights how poor scalability of current methods limits performance. Moreover, methods that use interventional information do not outperform those that only use observational data, contrary to what is observed on synthetic benchmarks. Thus, CausalBench opens new avenues in causal network inference research and provides a principled and reliable way to track progress in leveraging real-world interventional data.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 17 of its 83 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

17 of 83 references.

References · 17

  1. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  2. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  3. 2019Learning Sparse Nonparametric DAGscited by 207
  4. 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 165
  5. 2021Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Gamecited by 159
  6. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  7. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  8. 2022Amortized Inference for Causal Structure Learningcited by 89
  9. 2017Permutation-based Causal Inference Algorithms with Interventionscited by 78
  10. 2022Large-Scale Differentiable Causal Discovery of Factor Graphscited by 47
  11. 2020RealCause: Realistic Causal Inference Benchmarkingcited by 44
  12. 2021Learning Neural Causal Models with Active Interventionscited by 40
5 more
  1. 2018Benchmarking Framework for Performance-Evaluation of Causal Inference Analysiscited by 33
  2. 2019The Case for Evaluating Causal Models Using Interventional Measures and Empirical Datacited by 30
  3. 2022Validating Causal Inference Methodscited by 20
  4. 2021GeneDisco: A Benchmark for Experimental Design in Drug Discoverycited by 18
  5. 2019Size of Interventional Markov Equivalence Classes in Random DAG Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 6; 2025: 13; 2026: 2.

29 papers.

Sort:

By area:

  1. 2023CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discoverycited by 35
  2. 2025CausalRivers -- Scaling up benchmarking of causal discovery for real-world time-seriescited by 24
  3. 2024Sample, estimate, aggregate: A recipe for causal discovery foundation modelscited by 19
  4. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  5. 2023Learning DAGs from Data with Few Root Causescited by 8
  6. 2023The CausalBench challenge: A machine learning contest for gene network inference from single-cell perturbation datacited by 7
  7. 2025Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounderscited by 6
  8. 2025Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoptioncited by 6
  9. 2023Causality-oriented robustness: exploiting general noise interventionscited by 5
  10. 2023Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systemscited by 5
  11. 2024Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithmcited by 5
  12. 2025CausalMan: A physics-based simulator for large-scale causalitycited by 4
17 more
  1. 2025In-silico biological discovery with large perturbation modelscited by 4
  2. 2023Multi-omics Prediction from High-content Cellular Imaging with Deep Learningcited by 3
  3. 2023Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimationcited by 3
  4. 2023Assessing the overall and partial causal well-specification of nonlinear additive noise modelscited by 3
  5. 2025Achievable distributional robustness when the robust risk is only partially identifiedcited by 3
  6. 2025IGDA: Interactive Graph Discovery through Large Language Model Agentscited by 3
  7. 2025Causality-Inspired Robustness for Nonlinear Models via Representation Learningcited by 3
  8. 2024Simulation-based Benchmarking for Causal Structure Learning in Gene Perturbation Experimentscited by 2
  9. 2024Efficient Differentiable Discovery of Causal Ordercited by 2
  10. 2025Large Language Models for Zero-shot Inference of Causal Structures in Biologycited by 2
  11. 2025InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inferencecited by 1
  12. 2024Scalable Temporal Anomaly Causality Discovery in Large Systems: Achieving Computational Efficiency with Binary Anomaly Flag Datacited by 0
  13. 2025GPO-VAE: Modeling Explainable Gene Perturbation Responses utilizing GRN-Aligned Parameter Optimizationcited by 0
  14. 2025Addressing pitfalls in implicit unobserved confounding synthesis using explicit block hierarchical ancestral samplingcited by 0
  15. 2025Practical Causal Evaluation Metrics for Biological Networkscited by 0
  16. 2026When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Datacited by 0
  17. 2026Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Datacited by 0