Adaptive Node Feature Selection For Graph Neural Networks

• URL: http://arxiv.org/abs/2510.03096v1
• Date: Fri, 03 Oct 2025 15:26:11 GMT
• Title: Adaptive Node Feature Selection For Graph Neural Networks
• Authors: Ali Azizpour, Madeline Navarro, Santiago Segarra,
• Abstract summary: We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training.<n>Our empirical results verify the flexibility of our approach to different graph architectures as well as its adaptability to more challenging graph learning settings.
• Score: 45.44339759125884
• License: http://creativecommons.org/licenses/by/4.0/
• 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, reducing dimensionality, and even improving performance by eliminating unhelpful variables. However, graph-structured data introduces complex dependencies that may not be amenable to classical feature importance metrics. Inspired by this challenge, we present a 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 intervention-based approach by characterizing how GNN performance depends on the relationships between node data and graph structure. Not only do we return feature importance scores once training concludes, we also track how relevance evolves as features are successively dropped. We can therefore monitor if features are eliminated effectively and also evaluate other metrics with this technique. Our empirical results verify the flexibility of our approach to different graph architectures as well as its adaptability to more challenging graph learning settings.

Related papers

• Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning [37.735384483052044]
  Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based tasks (e.g., node classification or link prediction)<n>Despite their triumphs, GNNs still face challenges such as long training and inference times, difficulty in capturing complex relationships, and insufficient feature extraction.<n>We propose a novel framework combining graph prompts with weight pruning, called GPAWP, which aims to enhance the performance and efficiency of graph prompts by using fewer of them.
  arXiv  Detail & Related papers  (2025-07-12T04:12:24Z)
• Training Graph Neural Networks Using Non-Robust Samples [2.1937382384136637]
  Graph Neural Networks (GNNs) are highly effective neural networks for processing graph -- structured data.<n>GNNs leverage both the graph structure, which represents the relationships between data points, and the feature matrix of the data to optimize their feature representation.<n>This paper proposes a novel method for selecting noise-sensitive training samples from the original training set to construct a smaller yet more effective training set for model training.
  arXiv  Detail & Related papers  (2024-12-19T11:10:48Z)
• Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation [66.40525136929398]
  Test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain.<n>We propose Matcha, an innovative framework designed for effective and efficient adaptation to structure shifts in graphs.<n>We validate the effectiveness of Matcha on both synthetic and real-world datasets, demonstrating its robustness across various combinations of structure and attribute shifts.
  arXiv  Detail & Related papers  (2024-10-09T15:15:40Z)
• Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation [24.20087360102464]
  We study the dynamic graph unlearning for the first time and propose an effective, efficient, general, and post-processing method to implement DGNN unlearning.<n>Our method has the potential to handle future unlearning requests with significant performance gains.
  arXiv  Detail & Related papers  (2024-05-23T10:26:18Z)
• Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning [38.5372139056485]
  Graph Active Learning (GAL) aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance. Gal strategies may introduce semantic confusion to the selected training set, particularly when graphs are noisy. We present Semantic-aware Active learning framework for Graphs (SAG) to mitigate the semantic confusion problem.
  arXiv  Detail & Related papers  (2023-08-17T07:06:54Z)
• An Exploration of Conditioning Methods in Graph Neural Networks [8.532288965425805]
  In computational tasks such as physics and chemistry usage of edge attributes such as relative position or distance proved to be essential. We consider three types of conditioning; weak, strong, and pure, which respectively relate to concatenation-based conditioning, gating, and transformations that are causally dependent on the attributes. This categorization provides a unifying viewpoint on different classes of GNNs, from separable convolutions to various forms of message passing networks.
  arXiv  Detail & Related papers  (2023-05-03T07:14:12Z)
• GIF: A General Graph Unlearning Strategy via Influence Function [63.52038638220563]
  Graph Influence Function (GIF) is a model-agnostic unlearning method that can efficiently and accurately estimate parameter changes in response to a $epsilon$-mass perturbation in deleted data. We conduct extensive experiments on four representative GNN models and three benchmark datasets to justify GIF's superiority in terms of unlearning efficacy, model utility, and unlearning efficiency.
  arXiv  Detail & Related papers  (2023-04-06T03:02:54Z)
• Accurate Node Feature Estimation with Structured Variational Graph Autoencoder [21.436706159840014]
  Given a graph with partial observations of node features, how can we estimate the missing features accurately? We propose SVGA (Structured Variational Graph Autoencoder), an accurate method for feature estimation. As a result, SVGA combines the advantages of probabilistic inference and graph neural networks, achieving state-of-the-art performance in real datasets.
  arXiv  Detail & Related papers  (2022-06-09T14:07:45Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• Deep Reinforcement Learning of Graph Matching [63.469961545293756]
  Graph matching (GM) under node and pairwise constraints has been a building block in areas from optimization to computer vision. We present a reinforcement learning solver for GM i.e. RGM that seeks the node correspondence between pairwise graphs. Our method differs from the previous deep graph matching model in the sense that they are focused on the front-end feature extraction and affinity function learning.
  arXiv  Detail & Related papers  (2020-12-16T13:48:48Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.