FindAna is introduced, a GNN-assisted Foundation Model for Graph Anomaly Detection - the first foundation model framework designated for generalizable, cross-graph anomaly detection by combining GNNs and transformers.
Abstract
Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which supports critical applications in fraud detection, spam identification, network intrusion, etc. Despite the growing methods in the field, existing approaches follow a one-model-per-dataset paradigm, limiting their transferability across diverse real-world scenarios due to task heterogeneity, label scarcity, and domain variability. In this work, we introduce FoundAna, a GNN-assisted Foundation Model for Graph Anomaly Detection - the first foundation model framework designated for generalizable, cross-graph anomaly detection by combining GNNs and transformers. FoundAna integrates an anomaly detection-specific GNN component with a standard transformer encoder augmented by four complementary positional encodings, which enable the model to capture both local and global structural information. Specifically, the positional encoding enriched node representations are passed through attribute and adjacency decoders, and the reconstruction errors serve as the anomaly score. Extensive experiments on nine benchmark datasets spanning financial, social, and citation network domains demonstrate that FoundAna consistently outperforms state-of-the-art baselines. The code implementation and Supplementary materials are here: https://github.com/FoundAna331/FoundAna.
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.
Meng-Yu Li, Yong-Hao Liu, Xi-Ming Li et al.· IEEE Transactions on Pattern...· 0 citations
This work introduces a novel foundation model for TAG anomaly detection featuring decoupled topological and textual prototypes and constructs dual prototype banks to independently model structural normality and semantic consistency, effectively isolating anomaly cues that are otherwise diluted during coupled aggregatio...
Ziyang Wang, Liwen Wu, Cheng Xie et al.· 0 citations
Dynamic Multiscale Graph Contrastive Representation Learning (DMGCRL), a self-supervised framework that hierarchically models network intrusions at different levels, is proposed, which consistently outperforms SOTA methods in network intrusion detection.
Raeed Al-Sabri, Abdullatif Albaseer, Mohamed M. Abdallah et al.· IEEE Transactions on Network...· 0 citations
Static graph anomaly detection is important in applications such as cybersecurity, fraud detection, and social network analysis. However, detecting anomalies in attributed graphs remains challenging because of complex graph structures and limited labeled data. Existing methods often focus on either structural informati...
Hessa O. Alharbi, Hedia Zardi· Communications of Internatio...· 0 citations
LTRGAD is proposed, a two-stage GAD framework that performs feature selection based on local feature-topological residuals (LTR) and effectively introduces topological information while preserving the original local anomalous patterns, enabling more accurate local anomaly detection.
Ya-Zheng Zhao, Nan-Nan Wu, Hao Yin et al.· Proceedings of the Thirty-Fi...· 0 citations
It is suggested that graph construction quality, rather than mere graph presence, matters more for GNN performance than connectivity alone under the conditions evaluated here.
Roya Amiri, Sardar F. Jaf· Big Data and Cognitive Compu...· 0 citations
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.