Action Sequence Augmentation for Early Graph-based Anomaly Detection

Abstract

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.

arXiv commentCIKM'21

References in corpus (23)

• Sequence to Sequence Learning with Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Categorical Reparameterization with Gumbel-Softmax
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Large-Scale Learnable Graph Convolutional Networks
• Dynamic Graph Convolutional Networks
• A Semi-supervised Graph Attentive Network for Financial Fraud Detection
• Few-Shot Graph Learning for Molecular Property Prediction
• From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews
• Graph-based Anomaly Detection and Description: A Survey
• Interleaved Sequence RNNs for Fraud Detection
• Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps
• MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation
• Data Augmentation for Graph Neural Networks
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Neural Dynamics on Complex Networks
• Deep Learning to Address Candidate Generation and Cold Start Challenges in Recommender Systems: A Research Survey

Cited by in corpus (3)

• Few-Shot Graph Learning for Molecular Property Prediction
• Graph Rationalization with Environment-based Augmentations
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation