Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization

2025-12-20

AI Summary

To address the high cost of manual labeling prior to deploying Graph Neural Networks (GNNs), low test-case prioritization efficacy, and poor fault detection rates, this paper proposes GraphRank—a model-agnostic, graph-structure-aware iterative binary classification ranking framework. GraphRank’s core innovations include: (1) a joint attribute and graph-topology aggregation mechanism; (2) a dual-path feature extractor that simultaneously captures model-specific and model-agnostic signals; and (3) an iterative feedback loop to refine the ranking model. Crucially, GraphRank requires no modification to the target GNN, supports arbitrary GNN architectures, and explicitly encodes node relational structure. Extensive experiments across multiple GNN models and benchmark datasets demonstrate that GraphRank improves fault detection rate by 23.6% on average under fixed labeling budgets, significantly outperforming existing test prioritization methods.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in handling graph-structured data; however, they exhibit failures after deployment, which can cause severe consequences. Hence, conducting thorough testing before deployment becomes imperative to ensure the reliability of GNNs. However, thorough testing requires numerous manually annotated test data. To mitigate the annotation cost, strategically prioritizing and labeling high-quality unlabeled inputs for testing becomes crucial, which facilitates uncovering more model failures with a limited labeling budget. Unfortunately, existing test input prioritization techniques either overlook the valuable information contained in graph structures or are overly reliant on attributes extracted from the target model, i.e., model-aware attributes, whose quality can vary significantly. To address these issues, we propose a novel test input prioritization framework, named GraphRank, for GNNs. GraphRank introduces model-agnostic attributes to compensate for the limitations of the model-aware ones. It also leverages the graph structure information to aggregate attributes from neighboring nodes, thereby enhancing the model-aware and model-agnostic attributes. Furthermore, GraphRank combines the above attributes with a binary classifier, using it as a ranking model to prioritize inputs. This classifier undergoes iterative training, which enables it to learn from each round's feedback and improve its performance accordingly. Extensive experiments demonstrate GraphRank's superiority over existing techniques.

Problem

• Prioritizing unlabeled graph inputs for efficient GNN testing
• Addressing limitations in existing prioritization techniques for GNNs
• Reducing annotation costs while uncovering more model failures

Innovation

• Introduces model-agnostic attributes to complement model-aware attributes
• Leverages graph structure to aggregate attributes from neighboring nodes
• Uses an iteratively trained binary classifier for test input prioritization