If there are any areas, papers, and datasets I missed, please let me know!
- Causally Denoise Word Embeddings Using Half-Sibling Regression [pdf]
- A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations [pdf]
- [*] A Simultaneous Discover-Identify Approach to Causal Inference in Linear Models [pdf]
- [*] Explainable Reinforcement Learning Through a Causal Lens [pdf]
- Integrating overlapping datasets using bivariate causal discovery [pdf]
- Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning [pdf]
- CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines [pdf]
- Causal Transfer for Imitation Learning and Decision Making under Sensor-shift
- Recovering Causal Structures from Low-Order Conditional Independencies
- A Bayesian Approach for Estimating Causal Effects From Observational Data
- Estimating Causal Effects using Weighting-based Estimators
- A Calculus for Stochastic Interventions: Causal Effect Identification and Surrogate Experiment
- Multi-Source Causal Feature Selection
- [*] Counterfactuals uncover the modular structure of deep generative models [pdf]
- [*] Learning Disentangled Representations for CounterFactual Regression [pdf]
- [*] Learning The Difference That Makes A Difference With Counterfactually-Augmented Data [pdf]
- [*] Explanation by Progressive Exaggeration [pdf]
- [*] Estimating counterfactual treatment outcomes over time through adversarially balanced representations [pdf]
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms [pdf]
- [*] Causal Discovery with Reinforcement Learning [pdf]
- CoPhy: Counterfactual Learning of Physical Dynamics [pdf]
- [*] A Causal View on Robustness of Neural Networks [pdf]
- MissDeepCausal: causal inference from incomplete data using deep latent variable models [pdf]
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations [pdf]
- [*] Desiderata for Interpretability: Explaining Decision Tree Predictions with Counterfactuals [pdf]
- [*] Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology [pdf]
- [*] Scalable Causal Graph Learning through a Deep Neural Network [pdf]
- [*] The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations [pdf]
- [*] Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning [pdf]
- [*] Causal Embeddings for Recommendation: An Extended Abstract [pdf]
- Explaining Image Classifiers by Counterfactual Generation [pdf]
- [*] Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search [pdf]
- [*] CXPlain: Causal Explanations for Model Interpretation under Uncertainty [pdf]
- A Game Theoretic Approach to Class-wise Selective Rationalization [pdf]
- Causal Confusion in Imitation Learning
- Bayesian Counterfactual Risk Minimization [pdf]
- [*] Causal Identification under Markov Equivalence: Completeness Results [pdf]
- [*] Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models [pdf]
- Counterfactual Visual Explanations [pdf]
- [*] Deep Counterfactual Regret Minimization [pdf]
- [*] Learning to Generalize from Sparse and Underspecified Rewards [pdf]
- Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions [pdf]
- Validating Causal Inference Models via Influence Functions [pdf]
- Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness [pdf]
- [*] A causal framework for explaining the predictions of black box sequence to sequence models [pdf]
- [*] Generating Counterfactual Explanations with Natural Language [pdf] (ICML 2018 Workshop)
- [*] Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling [pdf] (arxiv)
- Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising [pdf] (JMLR 2013)