SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels

2025-02-05

AI Summary

Node anomaly detection (NAD) under extremely low-label regimes remains challenging due to weak representational capacity of single Euclidean-space models and overreliance on synthetic data augmentation. Method: This paper proposes a multi-space graph neural network framework featuring: (i) a learnable space projection function enabling joint embedding in both Euclidean and non-Euclidean spaces; (ii) a distance-aware message-passing mechanism grounded in weighted homophily theory to enhance local structural discrimination; and (iii) robust decision-making via multi-space representation ensembling—eliminating the need for data augmentation. Contribution/Results: Evaluated on nine real-world datasets, the method achieves average improvements of +8.55% in AUC and +4.31% in F1-score over state-of-the-art approaches, demonstrating superior performance and robustness in extremely low-label NAD settings.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Node Anomaly Detection (NAD) has gained significant attention in the deep learning community due to its diverse applications in real-world scenarios. Existing NAD methods primarily embed graphs within a single Euclidean space, while overlooking the potential of non-Euclidean spaces. Besides, to address the prevalent issue of limited supervision in real NAD tasks, previous methods tend to leverage synthetic data to collect auxiliary information, which is not an effective solution as shown in our experiments. To overcome these challenges, we introduce a novel SpaceGNN model designed for NAD tasks with extremely limited labels. Specifically, we provide deeper insights into a task-relevant framework by empirically analyzing the benefits of different spaces for node representations, based on which, we design a Learnable Space Projection function that effectively encodes nodes into suitable spaces. Besides, we introduce the concept of weighted homogeneity, which we empirically and theoretically validate as an effective coefficient during information propagation. This concept inspires the design of the Distance Aware Propagation module. Furthermore, we propose the Multiple Space Ensemble module, which extracts comprehensive information for NAD under conditions of extremely limited supervision. Our findings indicate that this module is more beneficial than data augmentation techniques for NAD. Extensive experiments conducted on 9 real datasets confirm the superiority of SpaceGNN, which outperforms the best rival by an average of 8.55% in AUC and 4.31% in F1 scores. Our code is available at https://github.com/xydong127/SpaceGNN.

Problem

• Detects node anomalies with limited labels
• Explores non-Euclidean spaces for graph embedding
• Introduces weighted homogeneity for information propagation

Innovation

• Multi-space node representation encoding
• Weighted homogeneity for information propagation
• Multiple Space Ensemble module utilization