Graph Neural Networks (GNNs) are widely applied for graph anomaly detection. As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum. Our crucial observation is the existence of anomalies will lead to the `right-shift' phenomenon, that is, the spectral energy distribution concentrates less on low frequencies and more on high frequencies. This fact motivates us to propose the Beta Wavelet Graph Neural Network (BWGNN). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the `right-shift' phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/Rethinking-Anomaly-Detection
Adversarial training is an approach for increasing model's resilience against adversarial perturbations. Such approaches have been demonstrated to result in models with feature representations that generalize better. However, limited works have been done on adversarial training of models on graph data. In this paper, we raise such a question { does adversarial training improve the generalization of graph representations. We formulate L2 and L1 versions of adversarial training in two powerful node embedding methods: graph autoencoder (GAE) and variational graph autoencoder (VGAE). We conduct extensive experiments on three main applications, i.e. link prediction, node clustering, graph anomaly detection of GAE and VGAE, and demonstrate that both L2 and L1 adversarial training boost the generalization of GAE and VGAE.
Anomalies represent rare observations (e.g., data records or events) that deviate significantly from others. Over several decades, research on anomaly mining has received increasing interests due to the implications of these occurrences in a wide range of disciplines. Anomaly detection, which aims to identify rare observations, is among the most vital tasks in the world, and has shown its power in preventing detrimental events, such as financial fraud, network intrusion, and social spam. The detection task is typically solved by identifying outlying data points in the feature space and inherently overlooks the relational information in real-world data. Graphs have been prevalently used to represent the structural information, which raises the graph anomaly detection problem - identifying anomalous graph objects (i.e., nodes, edges and sub-graphs) in a single graph, or anomalous graphs in a database/set of graphs. However, conventional anomaly detection techniques cannot tackle this problem well because of the complexity of graph data. For the advent of deep learning, graph anomaly detection with deep learning has received a growing attention recently. In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection. We compile open-sourced implementations, public datasets, and commonly-used evaluation metrics to provide affluent resources for future studies. More importantly, we highlight twelve extensive future research directions according to our survey results covering unsolved and emerging research problems and real-world applications. With this survey, our goal is to create a "one-stop-shop" that provides a unified understanding of the problem categories and existing approaches, publicly available hands-on resources, and high-impact open challenges for graph anomaly detection using deep learning.
The proliferation of web platforms has created incentives for online abuse. Many graph-based anomaly detection techniques are proposed to identify the suspicious accounts and behaviors. However, most of them detect the anomalies once the users have performed many such behaviors. Their performance is substantially hindered when the users' observed data is limited at an early stage, which needs to be improved to minimize financial loss. In this work, we propose Eland, a novel framework that uses action sequence augmentation for early anomaly detection. Eland utilizes a sequence predictor to predict next actions of every user and exploits the mutual enhancement between action sequence augmentation and user-action graph anomaly detection. Experiments on three real-world datasets show that Eland improves the performance of a variety of graph-based anomaly detection methods. With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.
Nowadays, graph-structured data are increasingly used to model complex systems. Meanwhile, detecting anomalies from graph has become a vital research problem of pressing societal concerns. Anomaly detection is an unsupervised learning task of identifying rare data that differ from the majority. As one of the dominant anomaly detection algorithms, One Class Support Vector Machine has been widely used to detect outliers. However, those traditional anomaly detection methods lost their effectiveness in graph data. Since traditional anomaly detection methods are stable, robust and easy to use, it is vitally important to generalize them to graph data. In this work, we propose One Class Graph Neural Network (OCGNN), a one-class classification framework for graph anomaly detection. OCGNN is designed to combine the powerful representation ability of Graph Neural Networks along with the classical one-class objective. Compared with other baselines, OCGNN achieves significant improvements in extensive experiments.
본 논문은 치환 및 관련 군(group)의 표현에 대한 등변(equivariant) 선형 레이어의 특성화를 탐구합니다. 매개변수 공유(parameter-sharing)를 통해 이러한 문제를 다루는 전통적인 접근법과 달리, 본 연구에서는 기약 표현(irreducible representation)과 슈어의 보조정리(Schur's lemma)에 기반한 대안적 방법론을 고려합니다. 이 방법론을 사용하여 DeepSets, 2-IGN 그래프 등변 네트워크, 딥 가중치 공간(DWS, Deep Weight Space) 네트워크와 같은 기존 모델에 대한 대안적 유도를 도출합니다. DWS 네트워크에 대한 유도는 기존 결과에 비해 훨씬 간단합니다. 나아가, 군의 화환곱(wreath product)에 대한 등변성이 요구되는 비정렬 대칭 집합으로 접근법을 확장합니다. 이전 연구들은 거의 모든 화환 등변 레이어가 샴(Siamese) 구조를 갖는 다소 제한적인 환경에서 이 문제를 다루었습니다. 이와 대조적으로, 본 논문에서는 이러한 경우의 레이어에 대한 완전한 특성화를 제시하며 일부 환경에서는 방대한 수의 추가적인 비-샴(non-Siamese) 레이어가 존재함을 보입니다. 또한 이러한 추가 비-샴 레이어가 그래프 이상치 탐지, 가중치 공간 정렬, 바세르슈타인 거리(Wasserstein distance) 학습과 같은 태스크에서 성능을 향상시킬 수 있음을 실증적으로 보여줍니다. 코드는 \href{https://github.com/yonatansverdlov/Irreducible-Representations-of-Deep-Weight-Spaces}{GitHub}에서 확인할 수 있습니다.