Adaptive Node Feature Selection For Graph Neural Networks

2025/10/03 by Madeline Navarro, Azizpour, Ali, Ali Azizpour +3
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2510.03096

openalex publication_date 2025/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training. The ability to measure how features contribute to model output is key for interpreting decisions and reducing dimensionality by eliminating unhelpful variables. However, graph-structured data introduces complex dependencies that may be unsuited to classical feature importance metrics. Inspired by this, we present a data-, model-, and task-agnostic method that determines relevant features during training based on changes in validation performance upon permuting feature values. We theoretically motivate our approach by characterizing how the relationships between node data and graph structure influences GNN performance. Empirically, we show that (i) our highly general approach rivals the performance of tailored feature selection approaches that exploit prior assumptions; (ii) we return meaningful feature importance scores well before the GNN is fully trained; and (iii) our scores demonstrably extract relevant properties that inform feature importance for various graph learning settings.

Citations

• Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discovery
• On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
• Redesigning graph filter-based GNNs to relax the homophily assumption
• A review of feature selection strategies utilizing graph data structures and knowledge graphs
• Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
• Mitigating Subpopulation Bias for Fair Network Topology Inference
• LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
• On Generalized Degree Fairness in Graph Neural Networks
• RAW-GNN: RAndom Walk Aggregation based Graph Neural Network
• On Structural Explanation of Bias in Graph Neural Networks
• Motif Graph Neural Network
• Simplifying approach to Node Classification in Graph Neural Networks
• Explainability in Graph Neural Networks: A Taxonomic Survey
• Explaining by Removing: A Unified Framework for Model Explanation
• Graph Neural Networks Including Sparse Interpretability
• Low-rank tensor methods for Markov chains with applications to tumor progression models
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Geom-GCN: Geometric Graph Convolutional Networks
• GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
• Feature Selection and Extraction for Graph Neural Networks
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance
• Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance
• Pitfalls of Graph Neural Network Evaluation
• How Powerful are Graph Neural Networks?
• L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
• Consistent Individualized Feature Attribution for Tree Ensembles
• A Permutation Test on Complex Sample Data
• Topology Adaptive Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Semi-Supervised Classification with Graph Convolutional Networks
• Distribution-Free Predictive Inference For Regression
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Image-based Recommendations on Styles and Substitutes
• When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
• A Comprehensive Survey on Graph Neural Networks

Related

• Feature Selection and Extraction for Graph Neural Networks
• Simplifying approach to Node Classification in Graph Neural Networks
• On Node Features for Graph Neural Networks
• Improving Graph Neural Networks with Simple Architecture Design
• Should Graph Neural Networks Use Features, Edges, Or Both?