pith. sign in

arxiv: 2204.04875 · v2 · pith:E4UD7GNZnew · submitted 2022-04-11 · 📊 stat.ML · cs.LG

Learning to Induce Causal Structure

Nan Rosemary Ke , Silvia Chiappa , Jane Wang , Anirudh Goyal , Jorg Bornschein , Melanie Rey , Theophane Weber , Matthew Botvinic
show 2 more authors
Michael Mozer Danilo Jimenez Rezende
This is my paper
classification 📊 stat.ML cs.LG
keywords graphscausaldatagraphinductioninterventionalobservationalstructure
0
0 comments X
read the original abstract

The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model generalizes to new synthetic graphs, is robust to train-test distribution shifts, and achieves state-of-the-art performance on naturalistic graphs for low sample complexity.

This paper has not been read by Pith yet.

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. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

    cs.LG 2022-07 conditional novelty 8.0

    TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single...

  2. Unsupervised Causal Abstractions Discovery

    cs.LG 2026-06 unverdicted novelty 6.0

    Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.

  3. Test Time Training for Supervised Causal Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    TTT-SCL dynamically generates test-aligned training sets for supervised causal learning using score-based functions and outperforms prior SCL and traditional causal discovery methods on benchmarks and real data.

  4. Amortized Inference of Causal Models via Conditional Fixed-Point Iterations

    cs.LG 2024-10 unverdicted novelty 6.0

    Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.

  5. 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.