ANOMIX: A Simple yet Effective Hard Negative Generation via Mixing for Graph Anomaly Detection
Graph contrastive learning (GCL) generally requires a large number of samples. The one of the effective ways to reduce the number of samples is using hard negatives (e.g., Mixup). Designing mixing-based approach for GAD can be difficult due to imbalanced data or limited number of anomalies. We propose ANOMIX, a framework that consists of a novel graph mixing approach, ANOMIX-M, and multi-level contrasts for GAD. ANOMIX-M can effectively mix abnormality and normality from input graph to generate hard negatives, which are important for efficient GCL. ANOMIX is (a) A first mixing approach: firstly attempting graph mixing to generate hard negatives for GAD task and node- and subgraph-level contrasts to distinguish underlying anomalies. (b) Accurate: winning the highest AUC, up to 5.49% higher and 1.76% faster. (c) Effective: reducing the number of samples nearly 80% in GCL. Code is available at https://github.com/missinghwan/ANOMIX.
Code (1)
Tasks
Anomaly DetectionContrastive LearningGraph Anomaly DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PanoMixSwap Panorama Mixing via Structural Swapping for Indoor Scene Understanding
The volume and diversity of training data are critical for modern deep learningbased methods. Compared to the massive amount of labeled perspective images, 360 panoramic images fall short in both volume and diversity. In…
Data AugmentationDiversityScene UnderstandingSemantic SegmentationDon't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
Training effective dense retrieval models often relies on hard negative (HN) examples mined from the document corpus via methods like BM25 or cross-encoders (CE), processes that can be computationally demanding and requi…
Large Language ModelRetrievalUnsupervised Training of Vision Transformers with Synthetic Negatives
This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synthetic hard negatives but rarely in the co…
Self-Supervised LearningRepresentation LearningMixKG: Mixing for harder negative samples in knowledge graph
Knowledge graph embedding~(KGE) aims to represent entities and relations into low-dimensional vectors for many real-world applications. The representations of entities and relations are learned via contrasting the positi…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsEnhanced Bayesian Personalized Ranking for Robust Hard Negative Sampling in Recommender Systems
In implicit collaborative filtering, hard negative mining techniques are developed to accelerate and enhance the recommendation model learning. However, the inadvertent selection of false negatives remains a major concer…
Collaborative FilteringRecommendation Systems