Rethinking Graph Neural Networks for Anomaly Detection

Tang, Jianheng; Li, Jiajin; Gao, Ziqi; Li, Jia

doi:10.48550/arxiv.2205.15508

Cited by 3 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following [31], the node representation g final A is fed into an MLP with the sigmoid activation function to compute the anomaly probabilities p A . The weighted cross entropy…”

Section: Graph Anomaly Detectionmentioning

confidence: 99%

“…Amazon dataset is used to detect anomalous users under the Musical Instrument Category on amazon.com [33]. T-Finance and T-Social datasets [31] are used for anomalous account detection in the transactions and social networks, respectively. For these four datasets, the graph is treated as a homogeneous graph (i.e.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…We compare with state-of-the-art approaches for graph anomaly detection, which include GraphConsis [34], CAREGNN [35], PC-GNN [36] and BWGNN [31]. Additionally, multi-layer perceptrons (MLP) and Graph Transformer (GT) [37] are included in the baselines for completeness.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…In [44] generative adversarial learning is used to detect anomaly nodes where a novel layer is designed to learn the anomaly-aware node representation. Recently, [31] pointed out that anomalies can lead to the "rightshift" of the spectral energy distribution -the spectral energy concentrates more on the high frequencies. They designed a filter that can better handle this phenomenon.…”

Section: B Details Of Et Training On Anomaly Detection Taskmentioning

confidence: 99%

“…where || is the concatenation sign. Following [31], we treat anomaly detection as semi-supervised learning task in this work. The node representation g final A is fed to another MLP with the sigmoid function to compute the abnormal probability p A , weighted log-likelihood is then used to train the network.…”

Section: B1 Detailed Model Structure For the Graph Anomaly Detectionmentioning

confidence: 99%

See 4 more Smart Citations

Energy Transformer

Hoover¹,

Liang²,

Pham³

et al. 2023

Preprint

View full text Add to dashboard Cite

Transformers have become the de facto models of choice in machine learning, typically leading to impressive performance on many applications. At the same time, the architectural development in the transformer world is mostly driven by empirical findings, and the theoretical understanding of their architectural building blocks is rather limited. In contrast, Dense Associative Memory models or Modern Hopfield Networks have a well-established theoretical foundation, but have not yet demonstrated truly impressive practical results. We propose a transformer architecture that replaces the sequence of feedforward transformer blocks with a single large Associative Memory model. Our novel architecture, called Energy Transformer (or ET for short), has many of the familiar architectural primitives that are often used in the current generation of transformers. However, it is not identical to the existing architectures. The sequence of transformer layers in ET is purposely designed to minimize a specifically engineered energy function, which is responsible for representing the relationships between the tokens. As a consequence of this computational principle, the attention in ET is different from the conventional attention mechanism. In this work, we introduce the theoretical foundations of ET, explore it's empirical capabilities using the image completion task, and obtain strong quantitative results on the graph anomaly detection task.

show abstract

“…Following [31], the node representation g final A is fed into an MLP with the sigmoid activation function to compute the anomaly probabilities p A . The weighted cross entropy…”

Section: Graph Anomaly Detectionmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: B Details Of Et Training On Anomaly Detection Taskmentioning

confidence: 99%

Section: B1 Detailed Model Structure For the Graph Anomaly Detectionmentioning

confidence: 99%

See 3 more Smart Citations

Energy Transformer

Hoover¹,

Liang²,

Pham³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning

Duan,

Zhang,

Wang

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

Graph anomaly detection (GAD) has attracted increasing attention in machine learning and data mining. Recent works have mainly focused on how to capture richer information to improve the quality of node embeddings for GAD. Despite their significant advances in detection performance, there is still a relative dearth of research on the properties of the task. GAD aims to discern the anomalies that deviate from most nodes. However, the model is prone to learn the pattern of normal samples which make up the majority of samples. Meanwhile, anomalies can be easily detected when their behaviors differ from normality. Therefore, the performance can be further improved by enhancing the ability to learn the normal pattern. To this end, we propose a normality learning-based GAD framework via multi-scale contrastive learning networks (NLGAD for abbreviation). Specifically, we first initialize the model with the contrastive networks on different scales. To provide sufficient and reliable normal nodes for normality learning, we design an effective hybrid strategy for normality selection. Finally, the model is refined with the only input of reliable normal nodes and learns a more accurate estimate of normality so that anomalous nodes can be more easily distinguished. Eventually, extensive experiments on six benchmark graph datasets demonstrate the effectiveness of our normality learning-based scheme on GAD. Notably, the proposed algorithm improves the detection performance (up to 5.

show abstract

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

Duan

Wang

Zhang

et al. 2023

AAAI

View full text Add to dashboard Cite

Graph anomaly detection (GAD) is a vital task in graph-based machine learning and has been widely applied in many real-world applications. The primary goal of GAD is to capture anomalous nodes from graph datasets, which evidently deviate from the majority of nodes. Recent methods have paid attention to various scales of contrastive strategies for GAD, i.e., node-subgraph and node-node contrasts. However, they neglect the subgraph-subgraph comparison information which the normal and abnormal subgraph pairs behave differently in terms of embeddings and structures in GAD, resulting in sub-optimal task performance. In this paper, we fulfill the above idea in the proposed multi-view multi-scale contrastive learning framework with subgraph-subgraph contrast for the first practice. To be specific, we regard the original input graph as the first view and generate the second view by graph augmentation with edge modifications. With the guidance of maximizing the similarity of the subgraph pairs, the proposed subgraph-subgraph contrast contributes to more robust subgraph embeddings despite of the structure variation. Moreover, the introduced subgraph-subgraph contrast cooperates well with the widely-adopted node-subgraph and node-node contrastive counterparts for mutual GAD performance promotions. Besides, we also conduct sufficient experiments to investigate the impact of different graph augmentation approaches on detection performance. The comprehensive experimental results well demonstrate the superiority of our method compared with the state-of-the-art approaches and the effectiveness of the multi-view subgraph pair contrastive strategy for the GAD task. The source code is released at https://github.com/FelixDJC/GRADATE.

show abstract

Rethinking Graph Neural Networks for Anomaly Detection

Cited by 3 publications

References 0 publications

Energy Transformer

Energy Transformer

Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

Contact Info

Product

Resources

About