arXiv:2510.25809v1 Announce Type: cross 
Abstract: Detecting anomalous nodes in attributed networks, where each node is associated with both structural connections and descriptive attributes, is essential for identifying fraud, misinformation, and suspicious behavior in domains such as social networks, academic citation graphs, and e-commerce platforms. We propose Flex-GAD, a novel unsupervised framework for graph anomaly detection at the node level. Flex-GAD integrates two encoders to capture complementary aspects of graph data. The framework incorporates a novel community-based GCN encoder to model intra-community and inter-community information into node embeddings, thereby ensuring structural consistency, along with a standard attribute encoder. These diverse representations are fused using a self-attention-based representation fusion module, which enables adaptive weighting and effective integration of the encoded information. This fusion mechanism allows automatic emphasis of the most relevant node representation across different encoders. We evaluate Flex-GAD on seven real-world attributed graphs with varying sizes, node degrees, and attribute homogeneity. Flex-GAD achieves an average AUC improvement of 7.98% over the previously best-performing method, GAD-NR, demonstrating its effectiveness and flexibility across diverse graph structures. Moreover, it significantly reduces training time, running 102x faster per epoch than Anomaly DAE and 3x faster per epoch than GAD-NR on average across seven benchmark datasets.

Flex-GAD هو إطار مبتكر مصمم لاكتشاف الشذوذ في الشبكات المعنونة، وهو أمر حيوي لتحديد الاحتيال والمعلومات المضللة عبر مجالات مختلفة مثل الشبكات الاجتماعية والتجارة الإلكترونية. تستخدم هذه الطريقة الجديدة مشفرين لتحليل كل من الروابط الهيكلية والسمات الوصفية للعقد، مما يجعلها تقدمًا كبيرًا في مجال اكتشاف الشذوذ في الرسوم البيانية. تتيح طبيعتها غير المشروطة تطبيقات أوسع، مما قد يحول طريقة مراقبتنا وإدارتنا للسلوكيات المشبوهة عبر الإنترنت.

Flex-GAD es un marco innovador diseñado para detectar anomalías en redes atribuidas, lo cual es crucial para identificar fraudes y desinformación en diversos dominios como redes sociales y comercio electrónico. Este enfoque utiliza dos codificadores para analizar tanto las conexiones estructurales como los atributos descriptivos de los nodos, lo que representa un avance significativo en el campo de la detección de anomalías en grafos. Su naturaleza no supervisada permite aplicaciones más amplias, transformando potencialmente nuestra forma de monitorear y gestionar comportamientos sospechosos en línea.

Flex-GAD est un cadre révolutionnaire conçu pour détecter les anomalies dans les réseaux attribués, ce qui est essentiel pour identifier la fraude et la désinformation dans divers domaines tels que les réseaux sociaux et le commerce électronique. Cette approche innovante utilise deux encodeurs pour analyser à la fois les connexions structurelles et les attributs descriptifs des nœuds, ce qui en fait une avancée significative dans le domaine de la détection d'anomalies dans les graphes. Sa nature non supervisée permet des applications plus larges, transformant potentiellement notre façon de surveiller et de gérer les comportements suspects en ligne.

Flex-GAD is a groundbreaking framework designed for detecting anomalies in attributed networks, which is crucial for identifying fraud and misinformation across various domains like social networks and e-commerce. This innovative approach utilizes two encoders to analyze both the structural connections and descriptive attributes of nodes, making it a significant advancement in the field of graph anomaly detection. Its unsupervised nature allows for broader applications, potentially transforming how we monitor and manage suspicious behaviors online.

Flex-GAD : Flexible Graph Anomaly Detection

arXiv:2601.08621v1 Announce Type: new 
Abstract: Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains such as e-commerce, social networks, and scientific citations, remains underexplored. Unlike plain text corpora, graphs encode rich topological signals that connect related entities and can serve as valuable priors for retrieval, enabling more targeted search and improved reasoning efficiency. Yet, effectively leveraging such structure poses unique challenges, including the difficulty of generating graph-expressive queries and ensuring reliable retrieval that balances structural and semantic relevance. To address this gap, we introduce GraphSearch, the first framework that extends search-augmented reasoning to graph learning, enabling zero-shot graph learning without task-specific fine-tuning. GraphSearch combines a Graph-aware Query Planner, which disentangles search space (e.g., 1-hop, multi-hop, or global neighbors) from semantic queries, with a Graph-aware Retriever, which constructs candidate sets based on topology and ranks them using a hybrid scoring function. We further instantiate two traversal modes: GraphSearch-R, which recursively expands neighborhoods hop by hop, and GraphSearch-F, which flexibly retrieves across local and global neighborhoods without hop constraints. Extensive experiments across diverse benchmarks show that GraphSearch achieves competitive or even superior performance compared to supervised graph learning methods, setting state-of-the-art results in zero-shot node classification and link prediction. These findings position GraphSearch as a flexible and generalizable paradigm for agentic reasoning over graphs.

تم تقديم إطار عمل جديد يسمى GraphSearch، الذي يوسع التفكير المعزز بالبحث إلى تعلم الرسوم البيانية، مما يمكّن التعلم من الرسوم البيانية بدون ضبط محدد للمهمة. هذا التقدم يعالج التحديات المتعلقة بالتعامل مع البيانات الهيكلية في الرسوم البيانية، والتي تزداد شيوعًا في مجالات متنوعة مثل التجارة الإلكترونية والشبكات الاجتماعية.

Se ha introducido un nuevo marco llamado GraphSearch, que extiende el razonamiento aumentado por búsqueda al aprendizaje de grafos, permitiendo el aprendizaje de grafos sin ajuste específico a la tarea. Este avance aborda los desafíos de operar con datos estructurados en grafos, que son cada vez más prevalentes en diversos dominios como el comercio electrónico y las redes sociales.

Un nouveau cadre nommé GraphSearch a été introduit, étendant le raisonnement augmenté par la recherche à l'apprentissage des graphes, permettant un apprentissage de graphes sans coupure spécifique à la tâche. Cette avancée répond aux défis liés à l'exploitation des données structurées en graphes, de plus en plus présentes dans divers domaines tels que le commerce électronique et les réseaux sociaux.

A new framework named GraphSearch has been introduced, extending search-augmented reasoning to graph learning, enabling zero-shot graph learning without the need for task-specific fine-tuning. This advancement addresses the challenges of operating on graph-structured data, which is increasingly prevalent in various domains such as e-commerce and social networks.

Flex-GAD : Flexible Graph Anomaly Detection

Was this article worth reading? Share it

LucidQuery AI

ZeroGPT.org

Graphite Note

Gyfted

GPTHumanizer

Adgrow

Ready to build your own newsroom?