A Survey of Learning Causality with Data: Problems and Methods

Abstract

This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era of big data different from -- or the same as -- the traditional one? To answer this question, this survey provides a comprehensive and structured review of both traditional and frontier methods in learning causality and relations along with the connections between causality and machine learning. This work points out on a case-by-case basis how big data facilitates, complicates, or motivates each approach.

35 pages, accepted by ACM CSUR

References in corpus (6)

• Feature Selection: A Data Perspective
• BART: Bayesian additive regression trees
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• Estimating treatment effect heterogeneity in randomized program evaluation
• Jointly interventional and observational data: estimation of interventional Markov equivalence classes of directed acyclic graphs
• The Identification and Estimation of Direct and Indirect Effects in A/B Tests through Causal Mediation Analysis

Cited by in corpus (33)

• A Tutorial on the Design, Experimentation and Application of Metaheuristic Algorithms to Real-World Optimization Problems
• Causality for Machine Learning
• Causal Understanding of Fake News Dissemination on Social Media
• Causal Intervention for Weakly-Supervised Semantic Segmentation
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• Visual Causality Analysis of Event Sequence Data
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
• Causality-based Feature Selection: Methods and Evaluations
• Causal Fourier Analysis on Directed Acyclic Graphs and Posets
• A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
• Distributed Learning of Generalized Linear Causal Networks
• Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix
• The Causal-Neural Connection: Expressiveness, Learnability, and Inference
• A Framework for Causal Discovery in non-intervenable systems
• Towards a Framework for Observational Causality From Time Series: When Shannon Meets Turing
• Adversarial Attacks and Defenses: An Interpretation Perspective
• Counterfactual Explanations for Machine Learning: Challenges Revisited
• A unified survey of treatment effect heterogeneity modeling and uplift modeling
• Interventional Video Grounding with Dual Contrastive Learning
• Efficient Neural Causal Discovery without Acyclicity Constraints
• Causal Learning for Socially Responsible AI
• Towards unique and unbiased causal effect estimation from data with hidden variables
• Automated Meta-Analysis: A Causal Learning Perspective
• Causal Mediation Analysis with Hidden Confounders
• High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
• Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication
• Causality in Static Models as an Initial Constraint on the Chronology of Events in System Behavior
• Identifying Causal Influences on Publication Trends and Behavior: A Case Study of the Computational Linguistics Community
• Undersmoothing Causal Estimators with Generative Trees
• Variational Auto-Encoder Architectures that Excel at Causal Inference
• Causal Impact of Web Browsing and Other Factors on Research Publications
• Exploiting non-i.i.d. data towards more robust machine learning algorithms
• Long-Term Effect Estimation with Surrogate Representation