Counterfactual Learning on Graphs: A Survey

Abstract

Graph-structured data are pervasive in the real-world such as social networks, molecular graphs and transaction networks. Graph neural networks (GNNs) have achieved great success in representation learning on graphs, facilitating various downstream tasks. However, GNNs have several drawbacks such as lacking interpretability, can easily inherit the bias of data and cannot model casual relations. Recently, counterfactual learning on graphs has shown promising results in alleviating these drawbacks. Various approaches have been proposed for counterfactual fairness, explainability, link prediction and other applications on graphs. To facilitate the development of this promising direction, in this survey, we categorize and comprehensively review papers on graph counterfactual learning. We divide existing methods into four categories based on problems studied. For each category, we provide background and motivating examples, a general framework summarizing existing works and a detailed review of these works. We point out promising future research directions at the intersection of graph-structured data, counterfactual learning, and real-world applications. To offer a comprehensive view of resources for future studies, we compile a collection of open-source implementations, public datasets, and commonly-used evaluation metrics. This survey aims to serve as a ``one-stop-shop'' for building a unified understanding of graph counterfactual learning categories and current resources. We also maintain a repository for papers and resources and will keep updating the repository https://github.com/TimeLovercc/Awesome-Graph-Causal-Learning.

References in corpus (67)

• Fast unfolding of communities in large networks
• A Comprehensive Survey on Graph Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Link Prediction in Complex Networks: A Survey
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Deep Learning based Recommender System: A Survey and New Perspectives
• Machine learning for molecular simulation
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Biological network comparison using graphlet degree distribution
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Social Structure of Facebook Networks
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Node Classification in Social Networks
• Contrastive Multi-View Representation Learning on Graphs
• GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems
• Causal Attention for Interpretable and Generalizable Graph Classification
• SIGN: Scalable Inception Graph Neural Networks
• Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Compositional Fairness Constraints for Graph Embeddings
• Causal Machine Learning: A Survey and Open Problems
• A Survey of Point-of-interest Recommendation in Location-based Social Networks
• Learning Fair Node Representations with Graph Counterfactual Fairness
• Just Train Twice: Improving Group Robustness without Training Group Information
• From Canonical Correlation Analysis to Self-supervised Graph Neural Networks
• CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks
• Representation Learning via Invariant Causal Mechanisms
• Survey on Causal-based Machine Learning Fairness Notions
• Unbiased Graph Embedding with Biased Graph Observations
• Robust Counterfactual Explanations on Graph Neural Networks
• CoPhy: Counterfactual Learning of Physical Dynamics
• Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases
• Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
• Towards Fair Graph Neural Networks via Graph Counterfactual
• Generative Causal Explanations for Graph Neural Networks
• Fair lending needs explainable models for responsible recommendation
• Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication
• Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods
• CLEAR: Generative Counterfactual Explanations on Graphs
• Desiderata for Representation Learning: A Causal Perspective
• Towards Faithful and Consistent Explanations for Graph Neural Networks
• DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
• FMP: Toward Fair Graph Message Passing against Topology Bias
• GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations
• Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
• Counterfactual Data Augmentation using Locally Factored Dynamics
• Fairness-Aware Node Representation Learning
• ECINN: Efficient Counterfactuals from Invertible Neural Networks
• Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
• Towards Prototype-Based Self-Explainable Graph Neural Network
• Deoscillated Graph Collaborative Filtering
• Improving Location Recommendation with Urban Knowledge Graph
• Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
• Fairness for Image Generation with Uncertain Sensitive Attributes
• On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach
• TopoImb: Toward Topology-level Imbalance in Learning from Graphs

Cited by in corpus (1)

• Finding Counterfactual Evidences for Node Classification