nacoyang/Causal_Reading_Group

We will keep updating the paper list about machine learning + causal theory. We also internally discuss related papers between NExT++ (NUS) and LDS (USTC) by week.

Causal_Reading_Group

This is a list of papers about causality.

Table of Contents

• Survey paper
• Dataset
• Foundamental Causality
• Causality in Machine Learning
• Causal Recommendation
• Causal Computer Vision
• Causality in NLP
• Causal Interpretability

Survey Paper

• D'ya like DAGs? A Survey on Structure Learning and Causal Discovery (2021)
• Causal Interpretability for Machine Learning -- Problems, Methods and Evaluation (2020KDD)
• A Survey of Learning Causality with Data: Problems and Methods (2020)
• A Survey on Causal Inference (2020)

Dataset

• ACIC 2018 Data Challenge (2018ACIC)

Foundamental Causality

• Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning (2021ICML)
• A Proxy Variable View of Shared Confounding (2021ICML)
• Valid Causal Inference with (Some) Invalid Instruments (2021ICML)
• Integer Programming for Causal Structure Learning in the Presence of Latent Variables (2021ICML)
• Operationalizing Complex Causes: A Pragmatic View of Mediation (2021ICML)
• Permutation Weighting (2021ICML)
• Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding (2021ICML)
• How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference (2021ICML)
• Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction (2021ICML)
• Model-Free and Model-Based Policy Evaluation when Causality is Uncertain (2021ICML)
• Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning (2019PNAS)
• Unit Selection Based on Counterfactual Logic (2019IJCAI)
• Counterfactual regression with importance sampling weights (2019IJCAI)
• Orthogonal Random Forest for Causal Inference (2019ICML)
• Estimation and Inference of Heterogeneous Treatment Effects using Random Forests (2018JASA)
• Estimating individual treatment effect: generalization bounds and algorithms (2017JMLR)
• Towards a learning theory of cause-effect inference (2015ICML)

Causality in Machine Learning

• Causal Reasoning in Simulation for Structure and Transfer Learning of Robot Manipulation Policies (2021ICRA)
• Generative Causal Explanations for Graph Neural Networks(2021ICML)
• Regularizing towards Causal Invariance: Linear Models with Proxies (2021ICML)
• Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners (2021ICML)
• On Disentangled Representations Learned from Correlated Data (2021ICML)
• [Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment] (2021ICML)
• Domain Generalization using Causal Matching (2021ICML)
• Selecting Data Augmentation for Simulating Interventions (2021ICML)
• Necessary and sufficient conditions for causal feature selection in time series with latent common causes (2021ICML)
• Out-of-Distribution Generalization via Risk Extrapolation (REx) (2021ICML)
• Counterfactual Credit Assignment in Model-Free Reinforcement Learning (2021ICML)
• Size-Invariant Graph Representations for Graph Classification Extrapolations (2021ICML)
• Adapting Interactional Observation Embedding for Counterfactual Learning to Rank (2021SIGIR)
• Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint(2021AISTATS)
• Path-specific Counterfactual Fairness (2019AAAI)
• Counterfactual Fairness (2017 NIPS)
• A Causal View on Robustness of Neural Networks (2020NeurIPS)
• An investigation of why overparameterization exacerbates spurious correlations (2020)
• Matching in Selective and Balanced Representation Space for Treatment Effects Estimation (2020CIKM)
• Improving the accuracy of medical diagnosis with causal machine learning (2020Nature Communication)
• Causal Meta-Mediation Analysis: Inferring Dose-Response Function From Summary Statistics of Many Randomized Experiments (2020KDD)
• Adapting Text Embeddings for Causal Inference (2020UAI)
• Double/Debiased/Neyman Machine Learning of Treatment Effects (2017American Economic Review)
• Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects(2020)
• Deep IV: A Flexible Approach for Counterfactual Prediction(2017)
• Estimating individual treatment effect: generalization bounds and algorithms(2017)
• Causal Decision Trees(2020)
• Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods(2018)

Causal Recommendation

• A Semi-Synthetic Dataset Generation Framework for Causal Inference in Recommender Systems (2021)
• [Recommending the Most Effective Interventions to Improve Employment for Job Seekers with Disability] (2021 KDD)
• Deconfounded Recommendation for Alleviating Bias Amplification (2021 KDD)
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System (2021 KDD)
• Causal Intervention for Leveraging Popularity Bias in Recommendation(2021 SIGIR)
• Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue (2021SIGIR)
• CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation (2021SIGIR)
• Personalized Counterfactual Fairness in Recommendation (2021SIGIR)
• Counterfactual Data-Augmented Sequential Recommendation (2021 SIGIR)
• Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback (2021SIGIR)
• Counterfactual Explanations for Neural Recommenders (2021SIGIR)
• The Simpson’s Paradox in the Offline Evaluation of Recommendation Systems(2021)
• PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems (2020WSDM)
• Counterfactual Prediction for Bundle Treatment (2020NeurIPS)
• Adversarial Counterfactual Learning and Evaluation for Recommender System (2020NeurIPS)
• Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback (2020NeurIPS)
• Learning Stable Graphs from Multiple Environments with Selection Bias (2020KDD)
• Causal Inference for Recommender Systems (2020 RecSys)
• Debiasing Item-to-Item Recommendations With Small Annotated Datasets (2020 RecSys)
• Deconfounding User Satisfaction Estimation from Response Rate Bias (2020 RecSys)
• Unbiased Learning for the Causal Effect of Recommendation (2020 RecSys)
• Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback (2020WSDM)
• A General Framework for Counterfactual Learning-to-Rank (2019SIGIR)
• Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random (2019ICML)
• Causal Embeddings for Recommendation: An Extended Abstract (2019IJCAI)
• Unbiased Learning to Rank with Unbiased Propensity Estimation (2018SIGIR)
• Recommendations as Treatments: Debiasing Learning and Evaluation (2016ICML)
• Estimating the Causal Impact of Recommendation Systems from Observational Data (2015ACMEC)
• Evaluating Online Ad Campaigns in a Pipeline: Causal Models At Scale (2010KDD)

Causal Computer Vision

• Interventional Video Grounding with Dual Contrastive Learning (2021CVPR)
• Deconfounded Video Moment Retrieval with Causal Intervention (2021SIGIR)
• Causal Attention for Vision-Language Tasks (2021CVPR)
• Deconfounded Image Captioning: A Causal Retrospect
• Counterfactual VQA: A Cause-Effect Look at Language Bias (2021CVPR)
• Visual Commonsense R-CNN (2020CVPR)
• More Grounded Image Captioning by Distilling Image-Text Matching Model (2020CVPR)
• Visual Commonsense Representation Learning via Causal Inference (2020CVPR)
• Counterfactual Samples Synthesizing for Robust Visual Question Answering (2020CVPR)
• Unbiased Scene Graph Generation From Biased Training (2020CVPR)
• Two Causal Principles for Improving Visual Dialog (2020CVPR)
• Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling (2020ECCV)

Causality in NLP

• Uncovering Main Causalities for Long-tailed Information Extraction (2021EMNLP)
• Empowering Language Understanding with Counterfactual Reasoning (2021ACL)
• Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis (2021NAACL)
• How to make causal inferences using texts (2018arxiv)
• Text and Causal Inference:A Review of Using Text to Remove Confounding from Causal Estimates (ACL2020)
• Causal inference of script knowledge (2020EMNLP)
• De-Biased Court’s View Generation with Causality (2020EMNLP)
• Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition (2020EMNLP)
• Counterfactual Off-Policy Training for Neural Dialogue Generation (2020EMNLP)
• Identifying Spurious Correlations for Robust Text Classification (2020EMNLP)
• Feature Selection as Causal Inference: Experiments with Text Classification (2017CoNLL)

Causal Interpretability

Causal Discovery

• CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models(2021CVPR)
• Disentangled Generative Causal Representation Learning
• Causal Inference with Deep Causal Graphs
• Causal Discovery with Reinforcement Learning(2020ICLR)
• Causal Discovery from Incomplete Data: A Deep Learning Approach(2020AAAI)
• A Graph Autoencoder Approach to Causal Structure Learning (2019-NeurIPS)
• CXPlain: Causal Explanations for Model Interpretation under Uncertainty (2019-NeurIPS)
• Neural Network Attributions: A Causal Perspective (2019-ICML)
• Building Causal Graphs from Medical Literature and Electronic Medical Records(2019-AAAI)
• Explaining Deep Learning Models Using Causal Inference (2018)
• Neural Relational Inference for Interacting Systems (2018-ICML)
• Learning Independent Causal Mechanisms (2018-ICML)
• DAGs with NO TEARS: Continuous Optimization for Structure Learning (2018-NeurIPS)
• A Causal Framework for Explaining the Predictions of Black-box Sequence-to-sequence Models (2017-EMNLP)

Causal Intervention

• Causal Intervention for Weakly-Supervised Semantic Segmentation (2020NeurIPS)
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (2020NeurIPS)
• Interventional Few-Shot Learning (2020NeurIPS)
• GAN Disssertion: Visualizing and Understnding Generative Adversarial Networks (2018ICLR)
• Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations (2018)

Counterfactual Interpretability

• Model-Based Counterfactual Synthesizer for Interpretation (2021 KDD)
• Counterfactual Explanations for Neural Recommenders (2021SIGIR)
• Algorithmic Recourse: from Counterfactual Explanations to Interventions (2021FAT)
• CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks (2021)
• Delta-CLUE Divere Sets of Explanations for Uncertainty Estimates (2021ICLR workshop)
• Explaining Deep Graph Networks with Molecular Counterfactuals (2020NeurIPS)
• Learning the Difference that Makes a Difference with Counterfactually-augmented Data (2020ICLR)
• Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition (2020EMNLP)
• Counterfactual Visual Explanations (2019ICML)
• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers (2019NeurIPS)
• Explaining Image Classifiers by Counterfactual Generation (2019ICLR)
• Interpretable Counterfactual Explanations Guided by Prototypes (2019)
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations (2019FAT)