The award‑winning industrial graph learning system developed by Peking University and Alibaba Mama combines novel dynamic graph embedding and GNN techniques, scales to millions of merchants, and has driven over 12% ad ROI improvement while publishing dozens of top‑conference papers.
This article reviews why large language models can be applied to graph learning, outlines their capabilities and graph data characteristics, surveys current research across different graph types and LLM roles, and proposes future research directions for unified cross‑domain graph learning.
This article reviews the evolution of graph technology, its applications in telecom, finance, and recommendation systems, discusses challenges of storage and querying large-scale graphs, and presents performance‑optimizing techniques for graph learning engines such as Wind.
This article presents a comprehensive overview of graph knowledge transfer, covering its definition, the data‑hungry problem, distribution shift challenges, the Knowledge Bridge Learning (KBL) framework, the Bridged‑GNN model, extensive experiments on real‑world scenarios, and a concluding Q&A session.
This article explains how large‑scale graph technology is applied to financial anti‑fraud, covering background, graph‑driven perception, analysis, decision‑making and enforcement, evolution of graph methods, a comprehensive risk‑control platform, and a Q&A on practical implementation.
In this talk, researcher Jiang Zhuoren from Zhejiang University reviews the current state of large language models applied to graph learning, discusses their roles across various graph scenarios, and outlines promising research directions for unified cross‑domain graph learning.
The IEEE ICDM 2023 Graph Learning Challenge, co‑hosted by Ant Group and Zhejiang University, showcased deep graph learning approaches for community detection and fraud‑group mining, highlighting the winning team's Risk‑DCRN method and emphasizing the importance of pretrained models in large‑scale network analysis.
TuGraph-DB v4.0, the open‑source graph database from Ant Group, introduces ISO GQL compliance, enterprise‑grade high availability with RAFT‑based leader election, and an integrated graph learning engine compatible with DGL and PyG, enhancing query capabilities, scalability, and AI‑driven analytics.
Ant Group announced the open-source release of Ant Graph Learning (AGL), a pioneering industrial‑grade graph learning platform that supports trillion‑scale graph data, offers ready‑to‑use algorithms, and aims to lower the barrier for large‑scale graph AI applications across industries.
This article presents Ant Group's use of graph machine learning for credit risk management, covering the background of small‑business lending, the proprietary AGL graph learning algorithms and system architecture, and detailed applications such as supply‑chain risk analysis, GMV prediction, and temporal graph‑based credit scoring.
PaddlePaddle 2.4 introduces 167 new APIs—including sparse computing (paddle.sparse), graph learning (paddle.geometric), and audio processing (paddle.audio) modules—enabling efficient sparse model training and inference, graph message‑passing, advanced audio feature extraction, plus fresh loss functions, tensor utilities, and expanded vision transforms.
This article provides an extensive overview of graph neural networks, tracing their evolution from early RNN‑based models to modern message‑passing frameworks, discussing complex graph types, diverse real‑world applications, scalability challenges, design spaces, training platforms, and promising research directions.
This article reviews the rapid development of privacy-preserving computation, explains its classification, discusses differential privacy, secure multi‑party computation, federated and split learning, and demonstrates how these techniques can be combined for graph learning and recommendation systems, culminating in a description of the JinZhiTa privacy‑computing platform.
This article presents how Ant Group leverages graph machine learning, including knowledge graph, social network, and cross-domain techniques, to enhance recommendation for low-activity users across scenarios such as fund, coupon, and waistband recommendations, detailing model architecture, challenges, solutions, and experimental results.
SMAD is a scalable graph‑based ad retrieval framework for e‑commerce search that builds a heterogeneous Query‑Item‑Ad graph, learns multi‑view embeddings with a parallel deep neural network and attention, employs category‑aware sampling for efficient distributed training, and delivers significant gains in offline relevance and online CTR, RPM, and PVR.
This article compiles and summarizes fifteen influential survey papers on Graph Neural Networks, covering their models, applications, datasets, benchmarks, challenges, and future directions, while providing links to the original PDFs and highlighting distinctions between small and large-scale graph learning.
