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

arXiv: https://arxiv.org/abs/2502.03201 · HTML: https://mlsanity.com/paper/2502.03201/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2025.

## Built on by (most cited first, 17 of 17)

- [Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs](https://mlsanity.com/paper/2502.17912/) (2025)
- [Tabular Foundation Models are Strong Graph Anomaly Detectors](https://mlsanity.com/paper/2601.17301/) (2026)
- [Semi-supervised Graph Anomaly Detection via Robust Homophily Learning](https://mlsanity.com/paper/2506.15448/) (2025)
- [CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection](https://mlsanity.com/paper/2605.20032/) (2026)
- [Computationally-efficient Graph Modeling with Refined Graph Random Features](https://mlsanity.com/paper/2510.07716/) (2025)
- [Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection](https://mlsanity.com/paper/2505.18934/) (2025)
- [Generalist Graph Anomaly Detection via Prototype-Based Distillation](https://mlsanity.com/paper/2605.26857/) (2026)
- [Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection](https://mlsanity.com/paper/2605.27470/) (2026)
- [Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection](https://mlsanity.com/paper/2605.29526/) (2026)
- [Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection](https://mlsanity.com/paper/2504.14250/) (2025)
- [FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision](https://mlsanity.com/paper/2509.20978/) (2025)
- [Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraud](https://mlsanity.com/paper/2601.11073/) (2026)
- [Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approach](https://mlsanity.com/paper/2603.08137/) (2026)
- [TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection](https://mlsanity.com/paper/2603.09349/) (2026)
- [Multimodal QUD: Inquisitive Questions from Scientific Figures](https://mlsanity.com/paper/2604.23733/) (2026)
- [The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly Detection](https://mlsanity.com/paper/2609.33370/) (2026)
- [Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning](https://mlsanity.com/paper/2609.34211/) (2026)

## Abstract (arXiv)

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.