Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 2838-2849· 0 citations· 35 references
Abstract
Temporal graph neural networks (T-GNNs) are powerful for representation learning on continuous-time dynamic graphs (CTDGs), but naively applying them to unsupervised anomaly detection is often unreliable. The key challenge is learning normal dynamics while being exposed to unlabeled anomalies, which destabilizes optimization and anomaly scoring. We further observe that gradient spikes are not unique to anomalies: many normal nodes also have large gradient norms. These nodes are typically sparse, offering limited temporal-structural context for message passing, so T-GNNs may mistake event sparsity for abnormality under an unsupervised setting. We term this phenomenon anomaly hallucination, which increases false positives and degrades detection performance. To address this challenge, we propose AHEAD, an unsupervised anti-hallucination anomaly detection framework featuring a hallucination refinement pipeline and a temporal-structural detector, which is compatible with various T-GNN backbones for reliable anomaly detection on CTDGs. For the refinement pipeline, we define a node-level uncertainty score that combines gradient norms and temporal-structural residuals to quantify optimization sensitivity, and then filter out high-sensitivity nodes for training the T-GNN backbone, which stabilizes gradient flow and improves representation learning. To sharpen the decision boundary, we propose an amplified divergence loss that ensures a wider discrepancy between normal dynamics and latent anomalies, reducing the false positive rate. Last, we theoretically and empirically show loss separability as a natural indicator of abnormality and build on this insight to develop a temporal-structural anomaly detector, improving detection performance. Extensive experiments demonstrate that the proposed AHEAD consistently improves anomaly detection accuracy, achieving up to 28.02% AUROC gains across five T-GNN backbones.
DGRA-CL transforms dynamic graphs into temporal sequences, employs time- and context-aware contrastive learning to learn normal node behavior patterns, retrieves similar normal exemplars from a training pool under a strict causality constraint, and fuses them via similarity-weighted aggregation to construct baseline representations.
Kamal Berahmand, S. Forouzandeh, Mehrnoush Mohammadi et al.· Annual International ACM SIG...· 2 citations
A novel framework, Generate and Filter graph learning for Graph Anomaly Detection (GFGAD), which generates a diverse set of synthetic anomalies with enriched feature and structural information to balance the data distribution and significantly outperforms state-of-the-art baselines.
Mengyu Li, Yonghao Liu, Ximing Li et al.· IEEE Transactions on Pattern...· 0 citations
BAD is proposed, an unsupervised framework for anomaly detection in continuous-time dynamic graphs that represents nodes with learnable identity embeddings and performs pairwise compatibility modeling via cross-attention between each destination node and the source’s recent neighbors, enabling direct characterization of context-dependent deviations without requiring attributes.
Jia-Chi Luo, Sha-Meng Wen, Ziyan Qiu et al.· 0 citations
Video Anomaly Detection (VAD) is a crucial computer vision task for
security monitoring and public safety. Unsupervised VAD is more suitable for
real-world scenarios with rare unknown anomalies, but existing LLM-based
methods suffer from limited temporal modeling, inconsistent video understand
ing and inaccurate fine-grained localization, leading to biased anomaly scoring.
To solve these problems, we propose a novel unsupervised VAD framework fus
ing graph attention propagation and multimodal semantic information: first, fuse
video semantic and motion features to construct a dynamic spatiotemporal graph,
and refine node features via graph attention propagation with orthogonal con
straints; then, split videos into semantically coherent event units by a statistical
boundary detection module; finally, guide MLLMs to generate event semantic
descriptions and initial anomaly scores through a hierarchical prompting strategy,
and refine the scores via video-text semantic alignment to obtain accurate frame
level scores. Evaluated on UCF-Crime and XD-Violence datasets with frame
level AUC, the proposed framework achieves state-of-the-art performance under
unsupervised and zero-shot settings, significantly outperforming existing LLM
based VAD methods and even several weakly supervised approaches, which fully
verifies its effectiveness and robustness.
Qinghao Kong· Poster Volume 0008 The 2026...· 0 citations
Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent ZSAD methods build on pretrained vision models, particularly CLIP, and construct normal and anomaly references from textual prompts or learnable visual representations. These methods perform anomaly discrimination primarily in spatial feature spaces, where subtle changes in texture, boundaries, and local structures can be confused with normal appearance variations. Although inconspicuous spatially, such defects can disrupt local texture regularity or boundary continuity, inducing response deviations across frequency bands. However, existing ZSAD methods do not explicitly model these frequency-dependent characteristics. Our image-domain analysis reveals that local defects exhibit spatial-frequency deviations from normal references across low-, middle-, and high-frequency bands, indicating that anomaly evidence is not universally dominated by high-frequency responses. Motivated by this observation, we propose FreqAnchorAD, a frequency-aware framework that organizes frequency-enhanced responses for anchor-relative anomaly discrimination. Specifically, the Local Frequency Compensation Module (LFCM) enhances intermediate patch tokens with local spatial-frequency cues. The Frequency-Deviation Anchor Projector (FDAP), our core discrimination module, organizes enhanced responses along a source-derived channel coordinate and measures anomaly evidence through relative similarity to normal and anomaly anchors. Finally, Asymmetric Anchor Supervision (AAS) stabilizes normal-anchor alignment while preserving diverse anomaly patterns. Experiments on thirteen industrial and medical benchmarks show that FreqAnchorAD achieves state-of-the-art mean performance in image-level anomaly recognition and pixel-level defect localization.
Jianfeng Qiu, Peiyuan Li, Juan Xie et al.· 0 citations
Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality unreliable. We introduce RINSE (Robust Iterative Normality Self-Estimation), a gradient-free target-time framework that keeps the source-trained detector fixed while sequentially estimating target normality, representation calibration, and evidence reliability from the target graph. Its core idea is to identify a reliable subset of low-residual target nodes, use them to construct a trimmed target-aware normality model, and combine complementary anomaly evidence through reliability-gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC among the evaluated methods under two separate preprocessing protocols, while block ablations and sensitivity analyses support the combined design. These results support robust target-time estimation as a practical approach to generalist graph anomaly detection without target labels, gradients, or per-target tuning.
Taufikur Rahman Fuad, Md Abrar Jahin, Amir Hussain· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
