no code implementations • 31 Jan 2025 • Xinshuai Dong, Ignavier Ng, Boyang Sun, Haoyue Dai, Guang-Yuan Hao, Shunxing Fan, Peter Spirtes, Yumou Qiu, Kun Zhang
Recent advances have shown that statistical tests for the rank of cross-covariance matrices play an important role in causal discovery.
no code implementations • 21 Jan 2025 • Minghao Fu, Biwei Huang, Zijian Li, Yujia Zheng, Ignavier Ng, Yingyao Hu, Kun Zhang
The study of learning causal structure with latent variables has advanced the understanding of the world by uncovering causal relationships and latent factors, e. g., Causal Representation Learning (CRL).
no code implementations • 29 Nov 2024 • Parjanya Prashant, Ignavier Ng, Kun Zhang, Biwei Huang
To the best of our knowledge, this is the first work to propose a differentiable causal discovery method for nonlinear latent hierarchical models.
no code implementations • 24 Oct 2024 • Kaifeng Jin, Ignavier Ng, Kun Zhang, Biwei Huang
Recent advances in differentiable structure learning have framed the combinatorial problem of learning directed acyclic graphs as a continuous optimization problem.
no code implementations • 8 Oct 2024 • Yingyu Lin, Yuxing Huang, Wenqin Liu, Haoran Deng, Ignavier Ng, Kun Zhang, Mingming Gong, Yi-An Ma, Biwei Huang
Real-world data often violates the equal-variance assumption (homoscedasticity), making it essential to account for heteroscedastic noise in causal discovery.
no code implementations • NeurIPS 2023 • Ignavier Ng, Yujia Zheng, Xinshuai Dong, Kun Zhang
To accommodate Gaussian sources, we develop an identifiability theory that relies on second-order statistics without imposing further preconditions on the distribution of sources, by introducing novel assumptions on the connective structure from sources to observed variables.
no code implementations • 11 Aug 2024 • Boyang Sun, Ignavier Ng, Guangyi Chen, Yifan Shen, Qirong Ho, Kun Zhang
Identifying the causal relations between interested variables plays a pivotal role in representation learning as it provides deep insights into the dataset.
no code implementations • 24 Jul 2024 • Xinshuai Dong, Ignavier Ng, Biwei Huang, Yuewen Sun, Songyao Jin, Roberto Legaspi, Peter Spirtes, Kun Zhang
Linear causal models are important tools for modeling causal dependencies and yet in practice, only a subset of the variables can be observed.
1 code implementation • 21 Mar 2024 • Haoyue Dai, Ignavier Ng, Gongxu Luo, Peter Spirtes, Petar Stojanov, Kun Zhang
This particular test-wise deletion procedure, in which we perform CI tests on the samples without zeros for the conditioned variables, can be seamlessly integrated with existing structure learning approaches including constraint-based and greedy score-based methods, thus giving rise to a principled framework for GRNI in the presence of dropouts.
1 code implementation • 21 Mar 2024 • Haoyue Dai, Ignavier Ng, Yujia Zheng, Zhengqing Gao, Kun Zhang
Local causal discovery is of great practical significance, as there are often situations where the discovery of the global causal structure is unnecessary, and the interest lies solely on a single target variable.
1 code implementation • 20 Feb 2024 • Loka Li, Ignavier Ng, Gongxu Luo, Biwei Huang, Guangyi Chen, Tongliang Liu, Bin Gu, Kun Zhang
This discrepancy has motivated the development of federated causal discovery (FCD) approaches.
no code implementations • 7 Feb 2024 • Kun Zhang, Shaoan Xie, Ignavier Ng, Yujia Zheng
We show that under the sparsity constraint on the recovered graph over the latent variables and suitable sufficient change conditions on the causal influences, interestingly, one can recover the moralized graph of the underlying directed acyclic graph, and the recovered latent variables and their relations are related to the underlying causal model in a specific, nontrivial way.
no code implementations • 18 Dec 2023 • Xinshuai Dong, Biwei Huang, Ignavier Ng, Xiangchen Song, Yujia Zheng, Songyao Jin, Roberto Legaspi, Peter Spirtes, Kun Zhang
Most existing causal discovery methods rely on the assumption of no latent confounders, limiting their applicability in solving real-life problems.
no code implementations • 19 May 2023 • Yujia Zheng, Ignavier Ng, Yewen Fan, Kun Zhang
A Markov network characterizes the conditional independence structure, or Markov property, among a set of random variables.
no code implementations • 4 Apr 2023 • Ignavier Ng, Biwei Huang, Kun Zhang
This paper investigates in which cases continuous optimization for directed acyclic graph (DAG) structure learning can and cannot perform well and why this happens, and suggests possible directions to make the search procedure more reliable.
1 code implementation • 30 Aug 2022 • Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
Recovering underlying Directed Acyclic Graph (DAG) structures from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem.
no code implementations • 15 Jun 2022 • Yujia Zheng, Ignavier Ng, Kun Zhang
We show that under specific instantiations of such constraints, the independent latent sources can be identified from their nonlinear mixtures up to a permutation and a component-wise transformation, thus achieving nontrivial identifiability of nonlinear ICA without auxiliary variables.
1 code implementation • 27 May 2022 • Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
1 code implementation • 17 Mar 2022 • Yuhao Kang, Kunlin Wu, Song Gao, Ignavier Ng, Jinmeng Rao, Shan Ye, Fan Zhang, Teng Fei
In this paper, we propose a Spatial Toeplitz Inverse Covariance-Based Clustering (STICC) method that considers both attributes and spatial relationships of geographic objects for multivariate spatial clustering.
1 code implementation • NeurIPS 2021 • Ignavier Ng, Yujia Zheng, Jiji Zhang, Kun Zhang
Many of the causal discovery methods rely on the faithfulness assumption to guarantee asymptotic correctness.
2 code implementations • 30 Nov 2021 • Keli Zhang, Shengyu Zhu, Marcus Kalander, Ignavier Ng, Junjian Ye, Zhitang Chen, Lujia Pan
$\texttt{gCastle}$ is an end-to-end Python toolbox for causal structure learning.
2 code implementations • 18 Oct 2021 • Ignavier Ng, Kun Zhang
Traditionally, Bayesian network structure learning is often carried out at a central site, in which all data is gathered.
1 code implementation • 23 Nov 2020 • Ignavier Ng, Sébastien Lachapelle, Nan Rosemary Ke, Simon Lacoste-Julien, Kun Zhang
Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity.
1 code implementation • NeurIPS 2020 • Ignavier Ng, AmirEmad Ghassami, Kun Zhang
Extensive experiments validate the effectiveness of our proposed method and show that the DAG-penalized likelihood objective is indeed favorable over the least squares one with the hard DAG constraint.
3 code implementations • 18 Nov 2019 • Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang
Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees.
2 code implementations • 18 Oct 2019 • Ignavier Ng, Shengyu Zhu, Zhuangyan Fang, Haoyang Li, Zhitang Chen, Jun Wang
This paper studies the problem of learning causal structures from observational data.
1 code implementation • ICLR 2020 • Shengyu Zhu, Ignavier Ng, Zhitang Chen
The reward incorporates both the predefined score function and two penalty terms for enforcing acyclicity.