Tagged articles
graph embedding
45 articles · Page 1 of 1
The 2015 LINE paper won the WWW 2026 Test of Time award, and its graph‑embedding principles that once powered web search, knowledge graphs, and recommendation systems now underpin GeoFlow models achieving AlphaFold‑level protein structure prediction and breakthrough antibody design, illustrating a ten‑year journey from web graphs to AI‑driven drug discovery.
AI for ScienceGeoFlowGraph Neural Networks
0 likes · 14 min read

The article presents the GEE (Graph Encoder Embedding) algorithm for business security anomaly detection, explains its label‑propagation foundation, evaluates it on ten‑million‑edge real data, identifies inefficiencies in the original implementation, and demonstrates that vectorized NumPy/Pandas optimizations reduce runtime from 55 seconds to about 4 seconds while preserving meaningful TSNE‑visualized embeddings.
Anti-FraudGEE algorithmanomaly detection
0 likes · 21 min read

Tencent’s Game Social Algorithm Team presents a Spark‑based distributed network embedding framework that recursively partitions hundred‑billion‑edge game graphs into manageable subgraphs, runs node2vec locally, and fuses results, enabling efficient link prediction and node classification across multiple games within hours.
Game AnalyticsSparkdistributed computing
0 likes · 7 min read

This article introduces the use of graph models in Baidu's recommendation system, covering graph fundamentals, common graph algorithms such as graph embedding and graph neural networks, the evolution of the Feed graph model, and its subsequent promotion across multiple product lines.
BaiduGraph Neural NetworksRecommendation System
0 likes · 10 min read


ArchitectJun 10, 2023 · Artificial Intelligence
Twitter’s recently open‑sourced recommendation system is dissected, covering its overall architecture, graph‑based data and feature engineering, recall pipelines (in‑network and out‑of‑network), coarse and fine ranking models, mixing and re‑ranking stages, as well as the supporting infrastructure and code examples.
Ranking ModelsRecommendation SystemTwitter
0 likes · 16 min read

This article presents EGES, a graph‑embedding model that incorporates side information to construct a directed user graph, apply biased random‑walk sampling, and train weighted Skip‑Gram embeddings, thereby improving large‑scale user acquisition and addressing cold‑start challenges in recommendation systems.
EGEScold startgraph embedding
0 likes · 9 min read

The article describes how YiduCloud builds real‑world medical knowledge graphs and clinical event graphs from heterogeneous hospital systems (EMR, HIS, LIS, RIS) using data aggregation, de‑identification, quality control, NLP‑driven entity extraction, standardisation, graph construction, cleaning, embedding and various AI‑powered applications such as decision support, intelligent diagnosis, automated medical‑record generation and patient recruitment.
AIMedical Knowledge GraphNLP
0 likes · 21 min read

This article explains how YiduCore processes heterogeneous hospital data (EMR, HIS, LIS, RIS, literature) to construct real‑world medical knowledge graphs and clinical event graphs, detailing pipelines for entity extraction, normalization, graph cleaning, PSR scoring, graph embedding, and showcasing applications such as intelligent diagnosis, question answering, automated medical record generation, and clinical trial patient recruitment.
AIMedical Knowledge GraphNLP
0 likes · 21 min read

This article introduces the fundamentals of recommendation systems, explains Zhuanzhuan's main recommendation scenarios and pipeline, and details three graph embedding methods—DeepWalk, node2vec, and EGES—along with their practical implementations in recall and coarse‑ranking stages.
DeepWalkEGESRecommendation System
0 likes · 17 min read

This article introduces VentureSights, an AI‑driven intelligent industry analysis platform built on knowledge‑graph technology and the concept of industry atoms, detailing its core modules, workflow, industry‑atom representation, extraction algorithms, and overall system architecture for generating comprehensive industry reports and insights.
Named Entity RecognitionSemantic Searchartificial intelligence
0 likes · 12 min read

This article presents AMCAD, an adaptive mixed‑curvature graph embedding system that models heterogeneous e‑commerce search ad graphs in non‑Euclidean spaces, detailing its sample construction, three‑stage model architecture, offline and online experiments, and demonstrating significant performance gains over Euclidean baselines.
advertisement retrievaldeep learninge-commerce
0 likes · 13 min read


HelloTechMay 26, 2022 · Artificial Intelligence
Hello’s automated C‑side growth algorithm loop integrates diverse traffic sources, semi‑supervised PU‑learning, graph‑based look‑alike targeting, causal uplift models for smart subsidies, and adaptive copy and external ad optimization, dramatically boosting ride‑hailing and lifestyle service revenue while minimizing engineering duplication.
AI PlatformUplift Modelinggraph embedding
0 likes · 20 min read

This article presents Hello Mobility’s precise marketing system, covering its business background, value, framework, algorithmic capabilities such as Pu‑Learning LookAlike modeling, TSA semi‑supervised learning, and Graph Embedding, as well as identified pain points, project impact, and future directions for scaling and automation.
AIgraph embeddinglookalike modeling
0 likes · 12 min read

This article presents Hello Mobility's precise marketing system, detailing its business background, value, framework, algorithmic capabilities—including Pu‑Learning LookAlike modeling, semi‑supervised TSA, and graph‑embedding techniques—addressing challenges such as sparse features and low ROI, and sharing performance improvements and future directions.
Pu-LearningROIgraph embedding
0 likes · 14 min read

This article introduces knowledge graphs, defining them as semantic networks or multi‑relational graphs, explains entities and relations, compares RDF and graph‑database storage, outlines construction steps including entity extraction and ontology building, reviews embedding models like TransE/H/R/D, and explores applications in search, finance, recommendation, and language models.
AIgraph embeddinginformation retrieval
0 likes · 22 min read

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.
Community DetectionGraphSAGEUnsupervised Learning
0 likes · 15 min read

This article explains how Douyu uses graph‑based algorithms to detect and mitigate fraudulent streaming traffic, covering the platform's risk‑control scenarios, the overall graph architecture, its evolution, modeling workflow, practical case studies, and the resulting improvements in detection accuracy and interpretability.
Graph AlgorithmsRisk Controlanti-cheat
0 likes · 16 min read

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.
Community DetectionGraphSAGEblack-gray-industry
0 likes · 12 min read

The article surveys six widely‑used graph‑embedding techniques—DeepWalk, Node2Vec, LINE, SDNE, EGES and Metapath2Vec—explaining how each transforms graph topology into low‑dimensional vectors via random walks, biased sampling, proximity‑based objectives, deep auto‑encoders, side‑information integration, or meta‑path‑guided walks for industrial applications.
DeepWalkEGESMetaPath2Vec
0 likes · 14 min read

This article surveys recent research on extracting and expanding hot topics from short texts by constructing user‑behavior graphs, applying graph‑embedding techniques, and leveraging multi‑task learning to improve recommendation relevance, timeliness, and cold‑start handling in large‑scale platforms.
artificial intelligencegraph embeddingknowledge graph
0 likes · 12 min read

Meituan’s search and NLP team announced that six knowledge‑graph papers—covering query‑aware tip generation, BERT‑based ranking, multi‑modal and sequential recommendation, conversational recommendation, and graph‑embedding for personalized product search—were accepted at CIKM 2020, resulting from university collaborations and already deployed to boost Meituan’s search, recommendation and product‑search services.
BERTCIKM 2020Multi-modal
0 likes · 13 min read

The article introduces Galileo, JD Retail's distributed graph deep‑learning platform that supports heterogeneous and dynamic graphs, ultra‑large scale training, flexible model customization, and seamless integration with TensorFlow and PyTorch, highlighting its architecture, core challenges, built‑in algorithms, and upcoming open‑source release.
AI PlatformGraph Neural Networksdistributed training
0 likes · 11 min read

This article reviews how skip‑gram‑based graph embedding methods such as DeepWalk, LINE and node2vec can be interpreted as matrix factorization, explains the NetMF and NetSMF frameworks that use sparse matrix approximations and random SVD for large‑scale networks, and discusses extensions like GATNE and deep clustering approaches to address practical challenges in constructing and applying graph representations.
Graph Neural NetworksSkip-gramgraph embedding
0 likes · 13 min read

This article introduces DyHAN, a dynamic heterogeneous graph embedding method that employs hierarchical attention across node, edge, and temporal dimensions to capture evolving user-item interactions, demonstrates superior performance over static and existing dynamic baselines, and reports significant online improvements in Alibaba’s recommendation system.
AlibabaAttention Mechanismdynamic graphs
0 likes · 9 min read

This article explains how Fliggy's travel recommendation platform tackles recall challenges such as cold‑start users, sparse behavior, itinerary‑specific needs, and periodic repurchase by applying user‑attribute models, graph embeddings, dual‑tower architectures, session‑based methods, and statistical repurchase forecasting to improve candidate selection and overall recommendation performance.
RecallTravelcold start
0 likes · 16 min read

This article explains the node2vec algorithm, its mathematical foundations, biased random‑walk sampling strategy with parameters p and q, implementation details using the Alias method, and demonstrates its superior performance on node classification and visualization tasks compared with DeepWalk and LINE.
Pythongraph embeddingmachine learning
0 likes · 9 min read

This article provides a comprehensive overview of graph embedding methods—including DeepWalk, LINE, node2vec, and EGES—explaining their algorithms, random‑walk strategies, proximity definitions, incorporation of side information, and their applications in large‑scale recommendation systems.
DeepWalkgraph embeddingline
0 likes · 20 min read

This article introduces DyHAN, a hierarchical attention‑based dynamic heterogeneous graph embedding method that captures temporal, node‑level, and edge‑level information, demonstrates superior offline and online performance on Alibaba’s ICBU recommendation system, and discusses dataset construction, model architecture, and future challenges.
DyHANHierarchical AttentionRecommendation System
0 likes · 10 min read

This article presents a comprehensive overview of graph‑based recommendation techniques, including collaborative filtering, graph embedding, side‑information enhanced embeddings, two‑tower DSSM models, and practical cold‑start strategies from Alibaba and Airbnb, followed by a mixed model and Q&A session.
AIcold startcollaborative filtering
0 likes · 14 min read

The talk explains how Beike Real Estate constructs a large‑scale relationship graph from billions of user, house, and agent interactions, quantifies edge strengths, builds homogeneous and heterogeneous sub‑graphs, derives graph capabilities such as node influence, embedding, similarity and relation prediction, and finally deploys these capabilities in multi‑degree queries, house‑similarity recommendations and B‑side agent assistance, achieving measurable CTR improvements.
AIRecommendation Systemgraph embedding
0 likes · 17 min read

This article surveys the development of recall modules in large‑scale recommendation systems, covering traditional item‑based collaborative filtering, single‑embedding DNN and dual‑tower approaches, multi‑interest capsule networks, graph‑based embeddings, long‑short term interest modeling, and the tree‑structured TDM framework for efficient deep matching.
deep learninggraph embeddingmulti‑interest
0 likes · 14 min read


Didi TechDec 2, 2019 · Artificial Intelligence
Didi’s Xiaoju Car Service leverages a reinforcement‑learning framework with Double DQN and graph‑embedding‑based personalization across its traffic‑distribution, tagging, portrait, targeting, strategy, and reach‑optimization modules, replacing manual rule‑based marketing, and achieves roughly 8 % new‑user lift, 50 % cost reduction, and significant gains in open and conversion rates.
Didigraph embeddingintelligent marketing
0 likes · 12 min read

This article describes how Didi Ride‑Sharing leverages reinforcement learning and graph‑embedding techniques to model and optimize user‑operation marketing, detailing system architecture, algorithm design, experimental ROI improvements, and personalized message delivery for enhanced conversion and cost efficiency.
DidiROIReinforcement Learning
0 likes · 11 min read

This article presents a comprehensive overview of short‑video recommendation at UC, covering business background, system architecture, the evolution from LR to Wide & Deep models, multi‑objective loss design with positive‑sample weighting, graph‑embedding fusion, time‑weighted loss, continuity modeling, a Boosting‑based WnD solution, and future research directions.
Multi-Objective OptimizationRecommendation Systemboosting
0 likes · 11 min read

This article introduces GATNE, a graph embedding framework that jointly models heterogeneous nodes, multiple edge types, and rich node attributes using base and edge embeddings, self‑attention, and inductive learning, and demonstrates its superior performance on several real‑world datasets.
GATNESelf-Attentiongraph embedding
0 likes · 8 min read

This article presents a comprehensive overview of Alibaba Retail's B2B2C intelligent recommendation platform, detailing its business context, three core recommendation scenarios, system architecture, matching algorithms such as item‑CF, graph embedding and user‑CF, as well as the evolution of ranking models and feature engineering practices.
AlibabaB2B2CPersonalization
0 likes · 17 min read

This article explains how graph‑based algorithms such as centrality measures, modularity optimization, Louvain, Infomap, node2vec and the comE framework can be applied to financial fraud detection and community discovery, detailing their principles, formulas, implementation steps and evaluation metrics.
Community DetectionGraph AlgorithmsInfomap
0 likes · 14 min read

This article reviews Alibaba’s year‑long Knowledge Engine program, detailing its five‑module architecture, major technical breakthroughs such as automatic ontology building and deep‑learning alignment, and two flagship research works: adversarial learning for crowdsourced NER and an iterative rule‑and‑embedding reasoning framework.
AINamed Entity Recognitionadversarial learning
0 likes · 9 min read

This article explains how graph embedding techniques, including a BSP‑based distributed LINE implementation and a cross‑category probabilistic graph model, are applied to improve the diversity and relevance of bundle (凑单) recommendations during large‑scale shopping events.
BSPLINE algorithmcross‑category
0 likes · 14 min read

This article explains how Alibaba's search team leverages AI techniques such as graph embedding, scenario‑based recommendation, and a multiple‑choice knapsack model to intelligently select complementary items during the Double Eleven shopping festival, balancing price constraints, user experience, and conversion efficiency.
e-commercegraph embeddingknapsack optimization
0 likes · 15 min read

This article explains how Alibaba builds a virtual category (CPV) system for Taobao by merging similar categories, splitting overly coarse ones, and constructing a hierarchical virtual category tree using methods such as PMI, title term similarity, frequent itemset mining, and graph‑embedding techniques, ultimately reducing user fatigue and improving CTR.
Taxonomycategory mergingcategory splitting
0 likes · 16 min read

An in‑depth look at Alibaba’s billion‑scale graph embedding framework—GES and EGES—reveals how side‑information‑enhanced embeddings address user long‑tail coverage and cold‑start challenges, improving recommendation diversity and discovery across massive e‑commerce datasets and enabling real‑time personalized ranking.
cold starte-commercegraph embedding
0 likes · 7 min read

Alibaba’s latest bundle‑mining system leverages weighted graph embedding and real‑time sampling to recommend complementary products, replacing traditional item‑to‑item similarity, boosting click‑through rates by up to 13% offline and 4% online during the Double‑11 promotion while handling billions of edges.
Recommendation Systembundle mininge-commerce
0 likes · 12 min read

This article explains how Alibaba's recommendation team built a large‑scale, AI‑driven personalization pipeline for the Double 11 shopping festival, using graph‑embedding recall, deep‑learning ranking models such as DeepResNet, DCN, and a custom XTensorflow platform to improve coverage, diversity, and click‑through rates.
AIRecommendation Systemdeep learning
0 likes · 20 min read

Alibaba’s merchant division introduced a scalable graph‑embedding approach for its “thousands‑of‑people‑one‑face” recommendation module, enabling personalized product suggestions within sparse shop data, improving click‑through rates by 30% and conversions by 60%, and presenting theoretical insights validated at AAAI 2017.
PersonalizationRecommendation Systeme-commerce
0 likes · 13 min read
