# Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method

arXiv: https://arxiv.org/abs/2010.11797 · HTML: https://mlsanity.com/paper/2010.11797/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 25 of 25)

- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [Deconfounded Video Moment Retrieval with Causal Intervention](https://mlsanity.com/paper/2106.01534/) (2021)
- [Learning from Counterfactual Links for Link Prediction](https://mlsanity.com/paper/2106.02172/) (2021)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [Empowering Language Understanding with Counterfactual Reasoning](https://mlsanity.com/paper/2106.03046/) (2021)
- [Unbiased Knowledge Distillation for Recommendation](https://mlsanity.com/paper/2211.14729/) (2022)
- [Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation](https://mlsanity.com/paper/2403.11960/) (2024)
- [Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering](https://mlsanity.com/paper/2402.11523/) (2024)
- [Exploring Causal Learning through Graph Neural Networks: An In-depth Review](https://mlsanity.com/paper/2311.14994/) (2023)
- [LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework](https://mlsanity.com/paper/2405.13902/) (2024)
- [CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks](https://mlsanity.com/paper/2402.14708/) (2024)
- [Deep Partial Multiplex Network Embedding](https://mlsanity.com/paper/2203.02656/) (2022)
- [Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention](https://mlsanity.com/paper/2305.13115/) (2023)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook](https://mlsanity.com/paper/2312.12477/) (2023)
- [Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks](https://mlsanity.com/paper/2404.03139/) (2024)
- [Cross-Domain Contract Element Extraction with a Bi-directional Feedback Clause-Element Relation Network](https://mlsanity.com/paper/2105.06083/) (2021)
- [Causally-guided Regularization of Graph Attention Improves Generalizability](https://mlsanity.com/paper/2210.10946/) (2022)
- [Graph Neural Network with Two Uplift Estimators for Label-Scarcity Individual Uplift Modeling](https://mlsanity.com/paper/2403.06489/) (2024)
- [Learning Robust Recommender from Noisy Implicit Feedback](https://mlsanity.com/paper/2112.01160/) (2021)
- [CausE: Towards Causal Knowledge Graph Embedding](https://mlsanity.com/paper/2307.11610/) (2023)
- [Counterfactual Graph Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2308.00391/) (2023)
- [Are All Edges Necessary? A Unified Framework for Graph Purification](https://mlsanity.com/paper/2211.05184/) (2022)
- [Decision Support System for Chronic Diseases Based on Drug-Drug Interactions](https://mlsanity.com/paper/2303.02405/) (2023)
- [Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges](https://mlsanity.com/paper/2505.08453/) (2025)

## Abstract (arXiv)

Graph Convolutional Network (GCN) is an emerging technique for information retrieval (IR) applications. While GCN assumes the homophily property of a graph, real-world graphs are never perfect: the local structure of a node may contain discrepancy, e.g., the labels of a node's neighbors could vary. This pushes us to consider the discrepancy of local structure in GCN modeling. Existing work approaches this issue by introducing an additional module such as graph attention, which is expected to learn the contribution of each neighbor. However, such module may not work reliably as expected, especially when there lacks supervision signal, e.g., when the labeled data is small. Moreover, existing methods focus on modeling the nodes in the training data, and never consider the local structure discrepancy of testing nodes. This work focuses on the local structure discrepancy issue for testing nodes, which has received little scrutiny. From a novel perspective of causality, we investigate whether a GCN should trust the local structure of a testing node when predicting its label. To this end, we analyze the working mechanism of GCN with causal graph, estimating the causal effect of a node's local structure for the prediction. The idea is simple yet effective: given a trained GCN model, we first intervene the prediction by blocking the graph structure; we then compare the original prediction with the intervened prediction to assess the causal effect of the local structure on the prediction. Through this way, we can eliminate the impact of local structure discrepancy and make more accurate prediction. Extensive experiments on seven node classification datasets show that our method effectively enhances the inference stage of GCN.