Causal learning has garnered significant attention in recent years because it reveals the essential relationships that underpin phenomena and delineates the mechanisms by which the world evolves. Nevertheless, traditional causal learning methods face numerous challenges and limitations, including high-dimensional, unstructured variables, combinatorial optimization problems, unobserved confounders, selection biases, and estimation inaccuracies. Deep causal learning, which leverages deep neural networks, offers innovative insights and solutions for addressing these challenges. Although numerous deep learning-based methods for causal discovery and inference have been proposed, there remains a dearth of reviews examining the underlying mechanisms by which deep learning can enhance causal learning. In this article, we comprehensively review how deep learning can contribute to causal learning by tackling traditional challenges across three key dimensions: representation, discovery, and inference. We emphasize that deep causal learning is pivotal for advancing the theoretical frontiers and broadening the practical applications of causal science. We conclude by summarizing open issues and outlining potential directions for future research.
Incorporating causal knowledge and mechanisms is essential for refining causal models and improving downstream tasks such as designing new treatments. In this paper, we introduce a novel concept in causal discovery, termed interventional constraints, which differs fundamentally from interventional data. While interventional data require direct perturbations of variables, interventional constraints encode high-level causal knowledge in the form of inequality constraints on causal effects. For instance, in the Sachs dataset (Sachs et al.\ 2005), Akt has been shown to be activated by PIP3, meanin…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Amazon（亚马逊）
We introduce a new Collaborative Causal Discovery problem, through which we model a common scenario in which we have multiple independent entities each with their own causal graph, and the goal is to simultaneously learn all these causal graphs. We study this problem without the causal sufficiency assumption, using Maximal Ancestral Graphs (MAG) to model the causal graphs, and assuming that we have the ability to actively perform independent single vertex (or atomic) interventions on the entities. If the $M$ underlying (unknown) causal graphs of the entities satisfy a natural notion of cluster…
Yield and quality improvement is of paramount importance to any manufacturing company. One of the ways of improving yield is through discovery of the root causal factors affecting yield. We propose the use of data-driven interpretable causal models to identify key factors affecting yield. We focus on factors that are measured in different stages of production and testing in the manufacturing cycle of a product. We apply causal structure learning techniques on real data collected from this line. Specifically, the goal of this work is to learn interpretable causal models from observational data …
Causal Discovery from Time-Series Data with Short-Term Invariance-Based Convolutional Neural Networks
Faculty of Computing（计算机学院）；Harbin Institute of Technology（哈尔滨工业大学）；The Artificial Intelligence Institute（人工智能研究所）；The Department of Computer Science（计算机科学系）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
causaLens（causaLens公司）；King’s College London（伦敦国王学院）
Causal discovery has become a vital tool for scientists and practitioners wanting to discover causal relationships from observational data. While most previous approaches to causal discovery have implicitly assumed that no expert domain knowledge is available, practitioners can often provide such domain knowledge from prior experience. Recent work has incorporated domain knowledge into constraint-based causal discovery. The majority of such constraint-based methods, however, assume causal faithfulness, which has been shown to be frequently violated in practice. Consequently, there has been ren…
Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions. With the growing importance of learning causal relationships, causal discovery tasks have transitioned from using traditional methods to infer potential causal structures from observational data to the field of pattern recognition involved in deep learning. The rapid accumulation of massive data promotes the emergence of causal search methods with brilliant scalability. Existing summaries of causal discovery methods mainly focus on traditional methods based on constra…
Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；ÉTS Montréal（蒙特利尔高等技术学院）
Learning predictors that do not rely on spurious correlations involves building causal representations. However, learning such a representation is very challenging. We, therefore, formulate the problem of learning a causal representation from high dimensional data and study causal recovery with synthetic data. This work introduces a latent variable decoder model, Decoder BCD, for Bayesian causal discovery and performs experiments in mildly supervised and unsupervised settings. We present a series of synthetic experiments to characterize important factors for causal discovery and show that usin…
Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
The University of Melbourne（墨尔本大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Peking University（北京大学）；Adelaide University（阿德莱德大学）；Hong Kong Baptist University（香港浸会大学）；The University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）
The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
School of Mathematics, Southeast University, Nanjing 210096, China（数学学院，东南大学，南京210096，中国）；School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China（网络科学与工程学院，东南大学，南京210096，中国）
We propose to address the task of causal structure learning from data in a supervised manner. Existing work on learning causal directions by supervised learning is restricted to learning pairwise relation, and not well suited for whole DAG discovery. We propose a novel approach of modeling the whole DAG structure discovery as a supervised learning. To fit the problem in hand, we propose to use permutation equivariant models that align well with the problem domain. We evaluate the proposed approach extensively on synthetic graphs of size 10,20,50,100 and real data, and show promising results co…
Informatics Institute（信息学研究所）；University of Amsterdam（阿姆斯特丹大学）
We address the problem of causal discovery from data, making use of the recently proposed causal modeling framework of modular structural causal models (mSCM) to handle cycles, latent confounders and non-linearities. We introduce σ-connection graphs (σ-CG), a new class of mixed graphs (containing undirected, bidirected and directed edges) with additional structure, and extend the concept of σ-separation, the appropriate generalization of the well-known notion of d-separation in this setting, to apply to σ-CGs. We prove the closedness of σ-separation under marginalisation and conditioning and e…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Conventional temporal causal discovery (CD) methods suffer from high dimensionality, fail to identify lagged causal relationships, and often ignore dynamics in relations. In this study, we present a novel constraint-based CD approach for autocorrelated and non-stationary time series data (eCDANs) capable of detecting lagged and contemporaneous causal relationships along with temporal changes. eCDANs addresses high dimensionality by optimizing the conditioning sets while conducting conditional independence (CI) tests and identifies the changes in causal relations by introducing a surrogate vari…
Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；ServiceNow Research（ServiceNow研究院）；Samsung AI Center Montreal（三星蒙特利尔人工智能中心）
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an equivalence class. Such classes, which are often large in size, encode uncertainties about the orientation of some edges in the causal graph. In this work, we propose a new set of assumptions that constrain possible causal relationships based on the nature of variables, thus circumscribing the equivalence class. Namely, we introduce typed directed acyclic graphs, in which variable types are used to determine the validity of causal relationships. We demonstrate, …
Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
University of Houston（德克萨斯大学休斯顿分校）；NEC Laboratories America（NEC美国实验室）；Florida International University（佛罗里达国际大学）；North Carolina State University（北卡罗来纳州立大学）
Learning to Defer for Causal Discovery with Imperfect Experts
University of Oxford（牛津大学）；Mila – Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；ServiceNow Research（ServiceNow研究院）；University of Amsterdam（阿姆斯特丹大学）；Université Laval（拉瓦尔大学）
Causal discovery from observational data is an important tool in many branches of science. Under certain assumptions it allows scientists to explain phenomena, predict, and make decisions. In the large sample limit, sound and complete causal discovery algorithms have been previously introduced, where a directed acyclic graph (DAG), or its equivalence class, representing causal relations is searched. However, in real-world cases, only finite training data is available, which limits the power of statistical tests used by these algorithms, leading to errors in the inferred causal model. This is c…
Can Large Language Models Help Experimental Design for Causal Discovery?
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Hong Kong Baptist University（香港浸会大学）；The University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
University of New South Wales（新南威尔士大学）；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；School of Computing, Macquarie University（麦考瑞大学计算学院）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织数据61）
The SINDy algorithm has been successfully used to identify the governing equations of dynamical systems from time series data. In this paper, we argue that this makes SINDy a potentially useful tool for causal discovery and that existing tools for causal discovery can be used to dramatically improve the performance of SINDy as tool for robust sparse modeling and system identification. We then demonstrate empirically that augmenting the SINDy algorithm with tools from causal discovery can provides engineers with a tool for learning causally robust governing equations.
University of Amsterdam（阿姆斯特丹大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
On time-series data, most causal discovery methods fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information which is lost when following this approach. Specifically, different samples may share the dynamics which describe the effects of their causal relations. We propose Amortized Causal Discovery, a novel framework that leverages such shared dynamics to learn to infer causal relations from time-series data. This enables us to train a single, amortized model that infers causal relations across samples with diffe…
It is crucial to consider the social and ethical consequences of AI and ML based decisions for the safe and acceptable use of these emerging technologies. Fairness, in particular, guarantees that the ML decisions do not result in discrimination against individuals or minorities. Identifying and measuring reliably fairness/discrimination is better achieved using causality which considers the causal relation, beyond mere association, between the sensitive attribute (e.g. gender, race, religion, etc.) and the decision (e.g. job hiring, loan granting, etc.). The big impediment to the use of causal…
Differentiable Causal Discovery For Latent Hierarchical Causal Models
University of California San Diego（加利福尼亚大学圣迭戈分校）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）；Graduate School of Arts and Sciences, The University of Tokyo（东京大学文理研究生院）
Causal structure discovery in complex dynamical systems is an important challenge for many scientific domains. Although data from (interventional) experiments is usually limited, large amounts of observational time series data sets are usually available. Current methods that learn causal structure from time series often assume linear relationships. Hence, they may fail in realistic settings that contain nonlinear relations between the variables. We propose Neural Additive Vector Autoregression (NAVAR) models, a neural approach to causal structure learning that can discover nonlinear relationsh…
KTH Royal Institute of Technology（KTH皇家理工学院）；Microsoft Research（微软研究院）
ChatGPT has demonstrated exceptional proficiency in natural language conversation, e.g., it can answer a wide range of questions while no previous large language models can. Thus, we would like to push its limit and explore its ability to answer causal discovery questions by using a medical benchmark (Tu et al. 2019) in causal discovery.
IE University（IE大学）；Universitat de València（瓦伦西亚大学）
Causal discovery algorithms aim at untangling complex causal relationships from data. Here, we study causal discovery and inference methods based on staged tree models, which can represent complex and asymmetric causal relationships between categorical variables. We provide a first graphical representation of the equivalence class of a staged tree, by looking only at a specific subset of its underlying independences. We further define a new pre-metric, inspired by the widely used structural intervention distance, to quantify the closeness between two staged trees in terms of their correspondin…
