SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection

• URL: http://arxiv.org/abs/2405.17525v2
• Date: Thu, 17 Oct 2024 08:56:51 GMT
• Title: SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection
• Authors: Xiangyu Dong, Xingyi Zhang, Yanni Sun, Lei Chen, Mingxuan Yuan, Sibo Wang,
• Abstract summary: We introduce Individual Smoothing Patterns (ISP) and Neighborhood Smoothing Patterns (NSP) ISP and NSP indicate that the representations of anomalous nodes are harder to smooth than those of normal ones. Motivated by these findings, we propose SmoothGNN, a novel unsupervised node anomaly detection framework.
• Score: 14.1365182085686
• License:
• Abstract: The smoothing issue in graph learning leads to indistinguishable node representations, posing significant challenges for graph-related tasks. However, our experiments reveal that this problem can uncover underlying properties of node anomaly detection (NAD) that previous research has missed. We introduce Individual Smoothing Patterns (ISP) and Neighborhood Smoothing Patterns (NSP), which indicate that the representations of anomalous nodes are harder to smooth than those of normal ones. In addition, we explore the theoretical implications of these patterns, demonstrating the potential benefits of ISP and NSP for NAD tasks. Motivated by these findings, we propose SmoothGNN, a novel unsupervised NAD framework. First, we design a learning component to explicitly capture ISP for detecting node anomalies. Second, we design a spectral graph neural network to implicitly learn ISP to enhance detection. Third, we design an effective coefficient based on our findings that NSP can serve as coefficients for node representations, aiding in the identification of anomalous nodes. Furthermore, we devise a novel anomaly measure to calculate loss functions and anomalous scores for nodes, reflecting the properties of NAD using ISP and NSP. Extensive experiments on 9 real datasets show that SmoothGNN outperforms the best rival by an average of 14.66% in AUC and 7.28% in Average Precision, with 75x running time speedup, validating the effectiveness and efficiency of our framework.

Related papers

• High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel Approach [0.0]
  This paper proposes a novel approach by introducing a High-Pass Graph Convolution Network (HP-GCN) for Graph Anomaly Detection (GAD) The proposed HP-GCN leverages high-frequency components to detect anomalies, as anomalies tend to increase high-frequency signals within the network of normal nodes. The model is evaluated and validated on YelpChi, Amazon, T-Finance, and T-Social datasets.
  arXiv  Detail & Related papers  (2024-11-04T05:38:07Z)
• Spiking Graph Neural Network on Riemannian Manifolds [51.15400848660023]
  Graph neural networks (GNNs) have become the dominant solution for learning on graphs. Existing spiking GNNs consider graphs in Euclidean space, ignoring the structural geometry. We present a Manifold-valued Spiking GNN (MSG) MSG achieves superior performance to previous spiking GNNs and energy efficiency to conventional GNNs.
  arXiv  Detail & Related papers  (2024-10-23T15:09:02Z)
• Understanding Virtual Nodes: Oversmoothing, Oversquashing, and Node Heterogeneity [4.59357989139429]
  Augmenting MPNNs with a virtual node (VN) has been found to improve performance on a range of benchmarks. We show that VNs typically avoid replicating anti-smoothing approaches to maintain expressive power. We propose a variant of VN with the same computational complexity, which can have different sensitivity to nodes based on the graph structure.
  arXiv  Detail & Related papers  (2024-05-22T10:51:12Z)
• Robust Node Representation Learning via Graph Variational Diffusion Networks [7.335425547621226]
  In recent years, compelling evidence has revealed that GNN-based node representation learning can be substantially deteriorated by perturbations in a graph structure. To learn robust node representation in the presence of perturbations, various works have been proposed to safeguard GNNs. We propose the Graph Variational Diffusion Network (GVDN), a new node encoder that effectively manipulates Gaussian noise to safeguard robustness on perturbed graphs.
  arXiv  Detail & Related papers  (2023-12-18T03:18:53Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• A Dimension-Augmented Physics-Informed Neural Network (DaPINN) with High Level Accuracy and Efficiency [0.20391237204597357]
  Physics-informed neural networks (PINNs) have been widely applied in different fields. We propose a novel dimension-augmented physics-informed neural network (DaPINN) DaPINN simultaneously and significantly improves the accuracy and efficiency of the PINN.
  arXiv  Detail & Related papers  (2022-10-19T15:54:37Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Edge Graph Neural Networks for Massive MIMO Detection [15.970981766599035]
  Massive Multiple-Input Multiple-Out (MIMO) detection is an important problem in modern wireless communication systems. While traditional Belief Propagation (BP) detectors perform poorly on loopy graphs, the recent Graph Neural Networks (GNNs)-based method can overcome the drawbacks of BP and achieve superior performance.
  arXiv  Detail & Related papers  (2022-05-22T08:01:47Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks [105.14867349802898]
  Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. GCNs tend to suffer performance drop when the model gets deep. We study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
  arXiv  Detail & Related papers  (2020-06-12T12:12:12Z)
• Stochastic Graph Neural Networks [123.39024384275054]
  Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning. Current GNN architectures assume ideal scenarios and ignore link fluctuations that occur due to environment, human factors, or external attacks. In these situations, the GNN fails to address its distributed task if the topological randomness is not considered accordingly.
  arXiv  Detail & Related papers  (2020-06-04T08:00:00Z)

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.