This article provides an introductory overview of graph neural networks, explaining their motivation, basic concepts, and detailing classic models such as GCN, GraphSAGE, GAT, Graph Auto‑Encoder, and DiffPool, along with their advantages, limitations, and experimental results on various benchmark datasets.
Graph Neural Networks (GNNs) have become a research hotspot, and this article provides an intuitive overview of classic GNN models such as GCN, GraphSAGE, GAT, graph auto‑encoders, and DiffPool, discussing their architectures, advantages, limitations, and experimental results across various benchmark datasets.
This article introduces graph modeling concepts, explains how they are applied to large‑scale information‑feed recall, details specific algorithms such as DeepWalk, LINE and GraphSAGE, describes feature engineering, loss design, training, deployment, evaluation, and discusses current challenges and future directions.
This article details how Shuhe Technology leveraged large‑scale graph neural networks, built with DGL and PyTorch, to improve financial fraud detection by preparing massive relationship graphs, pruning sparse nodes, extracting rich features, addressing class imbalance, and achieving a stable AUC gain of about four points.
This article presents a community‑encoding approach that leverages large‑scale graph‑embedding (GraphSAGE) and asynchronous near‑real‑time engineering to identify and measure unknown black‑gray market attacks with higher accuracy and flexibility than traditional graph‑mining methods.
The paper introduces a community‑encoding, GraphSAGE‑based detection framework that embeds whole user‑account, IP, device, and phone‑number graphs—both homogeneous and heterogeneous—to identify previously unseen black‑gray industry attacks, achieving about 95% IP‑risk accuracy via an asynchronous near‑real‑time system, though computational and automation challenges persist.
This article presents a comprehensive study on using graph representation learning, particularly GraphSAGE and its optimizations, to identify and mitigate black‑market accounts in virtual networks, covering background, algorithm design, handling isolated nodes and heterogeneity, and evaluation results.
This article presents a comprehensive overview of using graph representation learning and clustering, particularly GraphSAGE and its optimizations, to identify and mitigate black‑market (malicious) accounts in virtual networks, discussing background, objectives, challenges such as isolation and heterogeneity, and evaluation results.
This article introduces graph neural networks, explains their underlying sampling and aggregation mechanisms, and demonstrates how they are applied in large‑scale recommendation scenarios such as video and content feeds at Tencent, highlighting practical results and lessons learned.
This article introduces graph neural networks, explains their fundamentals and GraphSAGE/DGI algorithms, and demonstrates how Tencent applies them to recommendation scenarios such as video and WeChat content, highlighting network construction, feature engineering, sampling and aggregation techniques, and practical performance gains.
