Causality for Machine Learning

Abstract

Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence (AI), and for a long time had little connection to the field of machine learning. This article discusses where links have been and should be established, introducing key concepts along the way. It argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them.

References in corpus (17)

• External Validity: From Do-Calculus to Transportability Across Populations
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Water vapour in the atmosphere of the habitable-zone eight Earth-mass planet K2-18 b
• On the Identifiability of the Post-Nonlinear Causal Model
• On Causal and Anticausal Learning
• A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
• Inferring deterministic causal relations
• Causal Reasoning from Meta-reinforcement Learning
• Identifiability of Causal Graphs using Functional Models
• Towards a Learning Theory of Cause-Effect Inference
• Identifying confounders using additive noise models
• Independently Controllable Features
• Telling cause from effect based on high-dimensional observations
• Deconfounding Reinforcement Learning in Observational Settings
• From Ordinary Differential Equations to Structural Causal Models: the deterministic case
• Telling cause from effect in deterministic linear dynamical systems
• Causal Markov condition for submodular information measures

Cited by in corpus (67)

• Shortcut Learning in Deep Neural Networks
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Underspecification Presents Challenges for Credibility in Modern Machine Learning
• Weakly-Supervised Disentanglement Without Compromises
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Learning Invariant Representations for Reinforcement Learning without Reconstruction
• A causal view of compositional zero-shot recognition
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• On the Binding Problem in Artificial Neural Networks
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
• Instance-dependent Label-noise Learning under a Structural Causal Model
• Counterfactual Generative Networks
• Causal Navigation by Continuous-time Neural Networks
• Counterfactual Zero-Shot and Open-Set Visual Recognition
• White Paper Machine Learning in Certified Systems
• Distilling Causal Effect of Data in Class-Incremental Learning
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring
• Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
• Improving Generalizability of Fake News Detection Methods using Propensity Score Matching
• Urban Anomaly Analytics: Description, Detection, and Prediction
• Algorithms for Causal Reasoning in Probability Trees
• Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models
• Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Game
• Towards Automating the AI Operations Lifecycle
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• Latent Causal Invariant Model
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
• Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
• AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
• Unsuitability of NOTEARS for Causal Graph Discovery
• Patterns, predictions, and actions: A story about machine learning
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• Causality-aware counterfactual confounding adjustment for feature representations learned by deep models
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning
• Action-Sufficient State Representation Learning for Control with Structural Constraints
• Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
• Generative Interventions for Causal Learning
• A polynomial-time algorithm for learning nonparametric causal graphs
• iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
• Amortized learning of neural causal representations
• Identifying Causal Structure in Dynamical Systems
• Analysis of Drifting Features
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics
• Causal Multi-Agent Reinforcement Learning: Review and Open Problems
• Optimization-based Causal Estimation from Heterogenous Environments
• Learning Contextual Causality from Time-consecutive Images
• Harmonization with Flow-based Causal Inference
• No Representation without Transformation
• Path-specific Effects Based on Information Accounts of Causality
• Neural Networks for Learning Counterfactual G-Invariances from Single Environments
• Typing assumptions improve identification in causal discovery
• Exploiting non-i.i.d. data towards more robust machine learning algorithms
• Physical System for Non Time Sequence Data
• Inferring Causal Direction from Observational Data: A Complexity Approach
• Encoding Causal Macrovariables
• Towards intervention-centric causal reasoning in learning agents
• Learning Spatial Relationships between Samples of Patent Image Shapes
• Boxhead: A Dataset for Learning Hierarchical Representations
• Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
• GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
• VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries