BestHub
Sign in
Tagged articles
53 articles
Page 1 of 1
AI Engineering
AI Engineering
May 26, 2026 · Artificial Intelligence

Training Only the Skill Document While Keeping Model Weights Frozen (SkillOpt)

Microsoft Research introduces SkillOpt, a method that freezes large‑model weights and instead trains a natural‑language skill document as the sole learnable parameter, using a rollout‑reflect‑edit‑gate loop, achieving optimal results across 52 benchmark‑model‑environment combinations and demonstrating strong transferability.

LLM agentsSkillOptbenchmark evaluation
0 likes · 9 min read
Training Only the Skill Document While Keeping Model Weights Frozen (SkillOpt)
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 28, 2025 · Artificial Intelligence

Weekly Quantitative Finance Paper Digest (Nov 22‑28, 2025)

This digest summarizes five recent arXiv papers on AI-driven portfolio optimization and financial time‑series forecasting, covering G‑Learning with GIRL, transfer‑learning strategies, hybrid LSTM‑PPO frameworks, time‑series foundation models, and a KAN versus LSTM performance comparison, highlighting their methods, datasets, and reported Sharpe improvements.

Financial AIportfolio optimizationreinforcement learning
0 likes · 9 min read
Weekly Quantitative Finance Paper Digest (Nov 22‑28, 2025)
Data Party THU
Data Party THU
Nov 22, 2025 · Artificial Intelligence

How Frequency‑Refined Augmentation Boosts Contrastive Learning for Time‑Series Classification

FreRA introduces a lightweight, plug‑in frequency‑refined augmentation that adaptively refines spectral components to preserve global semantics while injecting variance, dramatically improving contrastive learning performance on time‑series classification, anomaly detection, and transfer learning across multiple benchmark datasets.

Time-seriescontrastive learningdata augmentation
0 likes · 13 min read
How Frequency‑Refined Augmentation Boosts Contrastive Learning for Time‑Series Classification
HyperAI Super Neural
HyperAI Super Neural
Sep 17, 2025 · Artificial Intelligence

How a CNN‑Transfer Learning Model Boosts Mumbai Monsoon Forecast Accuracy by 400% Using 36 Stations

A collaborative study between IIT Bombay and the University of Maryland creates a hyperlocal monsoon forecast model that downscales GFS data to city‑scale using 36 weather stations, event‑synchronization clustering, and transfer‑learned CNNs, achieving 60‑400% higher accuracy for extreme rainfall predictions several days in advance.

CNNEvent SynchronizationHyperlocal Prediction
0 likes · 12 min read
How a CNN‑Transfer Learning Model Boosts Mumbai Monsoon Forecast Accuracy by 400% Using 36 Stations
AntTech
AntTech
Mar 4, 2025 · Artificial Intelligence

GraphCLIP and 2D‑TPE: Enhancing Transferability of Graph Models and Table Understanding for Large Language Models

This article introduces GraphCLIP, a self‑supervised graph‑summary pre‑training framework that boosts zero‑ and few‑shot transferability of graph foundation models for text‑attributed graphs, and 2D‑TPE, a two‑dimensional positional encoding method that preserves table structure to markedly improve large language model performance on table‑understanding tasks, while also announcing a live paper session at WWW 2025 featuring the authors.

Positional EncodingSelf‑Supervised LearningTable Understanding
0 likes · 6 min read
GraphCLIP and 2D‑TPE: Enhancing Transferability of Graph Models and Table Understanding for Large Language Models
DaTaobao Tech
DaTaobao Tech
May 17, 2024 · Artificial Intelligence

Understanding Convolutional Neural Networks: Theory, Architecture, and Practical Techniques

The article explains CNN fundamentals—convolution, pooling, and fully‑connected layers—illustrates their implementation for American Sign Language letter recognition, details parameter calculations, demonstrates data augmentation and transfer learning techniques, and highlights how these methods boost image‑classification accuracy to around 92%.

CNNdata augmentationimage recognition
0 likes · 19 min read
Understanding Convolutional Neural Networks: Theory, Architecture, and Practical Techniques
DataFunSummit
DataFunSummit
Feb 17, 2024 · Artificial Intelligence

When to Pre‑Train Graph Neural Networks: Data‑Active Pre‑Training and a Graph Generator Framework

This article examines the conditions under which graph neural network pre‑training is beneficial, proposes a data‑centric generator framework to assess transferability, introduces a data‑active pre‑training strategy that selects informative graphs, and presents experimental results showing that using less, well‑chosen data can outperform full‑scale pre‑training.

Pre‑trainingdata selectiongraph generator
0 likes · 16 min read
When to Pre‑Train Graph Neural Networks: Data‑Active Pre‑Training and a Graph Generator Framework
DataFunTalk
DataFunTalk
May 24, 2023 · Artificial Intelligence

Graph Transfer Learning and VS-Graph: Knowledge Transferable Graph Neural Networks

This article reviews recent advances in graph transfer learning, introduces the novel VS-Graph scenario for knowledge transfer between dominant and silent nodes, and details the Knowledge Transferable Graph Neural Network (KTGNN) framework with domain‑adaptive feature completion, message passing, and transferable classifier modules, highlighting experimental results and future research directions.

AIKnowledge TransferVS-Graph
0 likes · 27 min read
Graph Transfer Learning and VS-Graph: Knowledge Transferable Graph Neural Networks
Python Crawling & Data Mining
Python Crawling & Data Mining
Mar 11, 2023 · Artificial Intelligence

How to Overcome Data Scarcity in Machine Learning: Strategies and Techniques

Facing data scarcity in machine learning, this article explores why large datasets are essential, categorizes missing data and label gaps, and presents practical solutions such as dataset reuse, augmentation, multimodal learning, curriculum learning, semi‑supervised methods, active learning, transfer and meta‑learning to mitigate the problem.

Machine LearningMeta Learningdata augmentation
0 likes · 19 min read
How to Overcome Data Scarcity in Machine Learning: Strategies and Techniques
Volcano Engine Developer Services
Volcano Engine Developer Services
Dec 15, 2022 · Artificial Intelligence

How Adaptive Transfer Kernels Boost Low‑Resource Regression: IEEE TPAMI Insights

The paper introduces adaptive transfer kernel learning for transfer Gaussian process regression, defines transfer kernels mathematically, proposes three generalized forms and two improved kernels, proves their positive‑semi‑definiteness, and demonstrates superior performance on low‑resource regression tasks through extensive experiments.

Gaussian ProcessMachine Learningkernel methods
0 likes · 9 min read
How Adaptive Transfer Kernels Boost Low‑Resource Regression: IEEE TPAMI Insights
DataFunTalk
DataFunTalk
Oct 15, 2022 · Artificial Intelligence

AutoDL: Automated and Interpretable Deep Learning – Research Highlights from Baidu Big Data Lab

This article reviews Baidu Big Data Lab's recent advances in automated deep learning (AutoDL), covering its research breakthroughs, integration with PaddlePaddle/PaddleHub, industrial deployments, transfer learning innovations, and future directions for AI automation and interpretability.

AI automationAutoDLNeural Architecture Search
0 likes · 19 min read
AutoDL: Automated and Interpretable Deep Learning – Research Highlights from Baidu Big Data Lab
DataFunSummit
DataFunSummit
Sep 8, 2022 · Artificial Intelligence

GAST: Graph Adaptive Semantic Transfer Model for Cross‑Domain Sentiment Analysis

This article introduces GAST, a graph‑adaptive semantic transfer framework that combines POS‑based Transformers and hybrid graph attention to improve cross‑domain sentiment analysis, presents related work, details the model architecture, reports extensive experiments showing state‑of‑the‑art results, and discusses future directions.

GAST modelNLPPOS tagging
0 likes · 13 min read
GAST: Graph Adaptive Semantic Transfer Model for Cross‑Domain Sentiment Analysis
DaTaobao Tech
DaTaobao Tech
Aug 30, 2022 · Artificial Intelligence

CTNet: Continual Transfer Learning for Cross-Domain Recommendation

CTNet is a continual transfer learning framework that uses a lightweight Adapter to map source‑domain features onto evolving target‑domain recommendation tasks, preserving all model parameters to avoid catastrophic forgetting and delivering substantial gains in click‑through rate, conversion, and overall business performance in Taobao’s cross‑domain e‑commerce scenario.

Adapter ModuleRecommendation Systemscontinual learning
0 likes · 12 min read
CTNet: Continual Transfer Learning for Cross-Domain Recommendation
DataFunSummit
DataFunSummit
Jul 25, 2022 · Artificial Intelligence

Intelligent Creative System at Hello: Business Background, Architecture, Implementation, and Reflections

This article presents Hello's Intelligent Creative project, detailing its business motivations, system architecture, algorithmic choices such as seq2seq, VAE, GAN, and pre‑trained models, the implementation of material libraries, tagging, recall strategies, a creative racing model, performance gains, and future challenges.

AICTR predictionad generation
0 likes · 16 min read
Intelligent Creative System at Hello: Business Background, Architecture, Implementation, and Reflections
Code DAO
Code DAO
Apr 24, 2022 · Artificial Intelligence

How Transfer Learning Accelerates Deep Learning Across Vision, NLP, and Reinforcement Learning

The article explains how transfer learning reduces data and time requirements in deep learning by reusing pretrained models for vision, natural language processing, and reinforcement learning, while discussing challenges such as overfitting, the need for progressive networks, entropy regularization, domain adaptation, multi‑task learning, and model distillation.

deep learningdomain adaptationmodel distillation
0 likes · 10 min read
How Transfer Learning Accelerates Deep Learning Across Vision, NLP, and Reinforcement Learning
DataFunTalk
DataFunTalk
Apr 21, 2022 · Artificial Intelligence

Solving Cold‑Start in Recommender Systems: The DropoutNet Approach

This article explains why cold‑start is a critical challenge for recommender systems, outlines four practical strategies—generalization, fast data collection, transfer learning, and few‑shot learning—and then details the DropoutNet model, its end‑to‑end training, loss functions, negative‑sampling techniques, and open‑source implementation.

DropoutNetEmbeddingcold start
0 likes · 21 min read
Solving Cold‑Start in Recommender Systems: The DropoutNet Approach
Baobao Algorithm Notes
Baobao Algorithm Notes
Feb 10, 2022 · Artificial Intelligence

Winning Kaggle’s Jigsaw Toxicity Challenge with Transfer Learning and Zero‑Shot Classification

This article breaks down the evolution of Kaggle’s Jigsaw toxic comment competitions and presents a three‑step solution—training on historic data, using a genetic algorithm to weight multi‑label predictions, and ensembling fifteen models—to achieve high‑accuracy zero‑shot text classification.

Artificial IntelligenceKaggleNLP
0 likes · 5 min read
Winning Kaggle’s Jigsaw Toxicity Challenge with Transfer Learning and Zero‑Shot Classification
Beike Product & Technology
Beike Product & Technology
Jan 7, 2022 · Artificial Intelligence

Beike Real Estate NLP Team Wins First Place in CCIR Cup 2021 Intelligent Human‑Computer Interaction Track

The Beike Real Estate NLP team secured first place in the CCIR Cup 2021 Intelligent Human‑Computer Interaction track by applying semi‑supervised and transfer learning techniques to small‑sample intent recognition and slot filling, and also presented the large‑scale Mandarin dialect speech benchmark KeSpeech at NeurIPS 2021.

AI competitionBERTNLP
0 likes · 5 min read
Beike Real Estate NLP Team Wins First Place in CCIR Cup 2021 Intelligent Human‑Computer Interaction Track
DataFunTalk
DataFunTalk
Dec 24, 2021 · Artificial Intelligence

Large-Scale Pretrained Model Compression and Distillation: AdaBERT, L2A, and Meta‑KD

This article reviews three consecutive works from Alibaba DAMO Academy on compressing and distilling large pretrained language models—AdaBERT, L2A, and Meta‑KD—detailing their motivations, neural‑architecture‑search‑based designs, loss formulations, experimental results, and insights from a Q&A session.

AIKnowledge DistillationModel Compression
0 likes · 10 min read
Large-Scale Pretrained Model Compression and Distillation: AdaBERT, L2A, and Meta‑KD
DataFunSummit
DataFunSummit
Dec 11, 2021 · Artificial Intelligence

Survey of User Representation Learning and Transfer Learning in Recommendation Systems

This article reviews recent advances in user representation learning for recommender systems, covering self‑supervised pre‑training, lifelong learning, multi‑task modeling, and large‑scale contrastive methods, and provides code and dataset links for key papers such as PeterRec, Conure, DUPN, ShopperBERT, PTUM, UPRec, and LURM.

Recommendation Systemspretrainingself-supervised learning
0 likes · 11 min read
Survey of User Representation Learning and Transfer Learning in Recommendation Systems
Code DAO
Code DAO
Dec 8, 2021 · Artificial Intelligence

Optimizers and Schedulers in Neural Network Architecture: A Detailed Guide

This article explains how optimizers and learning‑rate schedulers work, how to configure their hyperparameters and parameter groups, and how to apply differential learning rates and adaptive schedules in PyTorch and Keras to improve model training and transfer‑learning performance.

KerasPyTorchhyperparameter tuning
0 likes · 10 min read
Optimizers and Schedulers in Neural Network Architecture: A Detailed Guide
Code DAO
Code DAO
Dec 2, 2021 · Artificial Intelligence

Transfer Learning with ShuffleNetV2 for Flower Classification

This article walks through building a PyTorch ShuffleNetV2 model, preparing the Kaggle Flowers dataset, training with transfer learning on a GPU, visualizing loss and accuracy, and performing inference on five test images, achieving nearly 90% validation accuracy after 95 epochs.

CNNPyTorchShuffleNetV2
0 likes · 19 min read
Transfer Learning with ShuffleNetV2 for Flower Classification
Code DAO
Code DAO
Nov 30, 2021 · Artificial Intelligence

How to Train a Custom Object Detector with PyTorch Faster R‑CNN

This article provides a step‑by‑step guide to building, training, and evaluating a custom object detection model using PyTorch Faster R‑CNN on a microcontroller dataset, covering data preparation, configuration, model modification, training loops, loss visualization, and inference on new images.

Faster R-CNNPyTorchPython
0 likes · 23 min read
How to Train a Custom Object Detector with PyTorch Faster R‑CNN
DataFunSummit
DataFunSummit
Sep 30, 2021 · Artificial Intelligence

Transfer Learning for Financial Risk Control: Theory, Methods, and Empirical Results

This article introduces the fundamentals of transfer learning, formalizes its theoretical foundations, and demonstrates how multi‑task learning and domain adaptation techniques can be applied to financial risk control to overcome label scarcity, distribution shift, and improve model performance.

Artificial Intelligencedomain adaptationfinancial risk control
0 likes · 17 min read
Transfer Learning for Financial Risk Control: Theory, Methods, and Empirical Results
DataFunTalk
DataFunTalk
Sep 27, 2021 · Artificial Intelligence

Transfer Learning for Financial Risk Control: Theory, Methods, and Empirical Evaluation

This article introduces the fundamentals of transfer learning, explains its theoretical foundations and formulas, and demonstrates how multi‑task learning and domain‑adaptation techniques are applied to financial risk‑control scenarios to overcome label scarcity, distribution shift, and model complexity challenges, presenting detailed experimental results and analysis.

deep learningdomain adaptationfinancial risk
0 likes · 17 min read
Transfer Learning for Financial Risk Control: Theory, Methods, and Empirical Evaluation
DataFunTalk
DataFunTalk
Jul 1, 2021 · Artificial Intelligence

Pre‑Trained Models: Past, Present, and Future – A Comprehensive Survey

This article surveys the evolution of pre‑trained models, covering the origins of transfer and self‑supervised learning, the rise of transformer‑based PTMs such as BERT and GPT, efficient architecture designs, multimodal and multilingual extensions, theoretical analyses, and future research directions for scalable and robust AI systems.

AI researchMultimodalefficient training
0 likes · 27 min read
Pre‑Trained Models: Past, Present, and Future – A Comprehensive Survey
Ctrip Technology
Ctrip Technology
Dec 10, 2020 · Artificial Intelligence

Automatic Extraction of Theme-based Recommendation Reasons: Framework, Model Selection, Data Augmentation, and Optimization

This article presents a comprehensive study on automatically extracting theme‑based recommendation reasons for travel content, detailing a three‑stage retrieval framework, the advantages of interactive matching models over classification, rule‑based and back‑translation data augmentation techniques, and various model optimization strategies including priors, transfer learning, seed selection, optimizer choice, and layer‑wise learning rates.

AIRecommendation Systemsdata augmentation
0 likes · 19 min read
Automatic Extraction of Theme-based Recommendation Reasons: Framework, Model Selection, Data Augmentation, and Optimization
JD Tech Talk
JD Tech Talk
Oct 12, 2020 · Artificial Intelligence

Transfer Learning for Human Mobility Modeling in New Cities

The paper presented at WWW 2020 proposes a transfer‑learning framework that leverages POI, road‑network and traffic data from existing cities to generate realistic human mobility trajectories for a target city by modeling mobility intentions, origin‑destination pairs, and routes, and validates the approach with extensive experiments across multiple Chinese cities.

AIUrban Computingdomain generalization
0 likes · 10 min read
Transfer Learning for Human Mobility Modeling in New Cities
JD Tech Talk
JD Tech Talk
Sep 30, 2020 · Artificial Intelligence

Secure Training Methods for Federated Transfer Learning

This article reviews the model structure of federated transfer learning and details three secure training approaches—additive homomorphic encryption, ABY, and SPDZ—combined with polynomial approximation, explaining their protocols, steps, and the role of federated transfer learning within the broader federated learning landscape.

Homomorphic Encryptionprivacysecure computation
0 likes · 11 min read
Secure Training Methods for Federated Transfer Learning
JD Tech Talk
JD Tech Talk
Sep 17, 2020 · Artificial Intelligence

Federated Transfer Learning: Concepts, Examples, and Model Structures

This article introduces the fundamentals of transfer learning and federated transfer learning, explains domain adaptation for sentiment analysis, presents two illustrative examples—mid-level image feature transfer and text-to-image transfer—and outlines the model architecture and loss functions of federated transfer learning frameworks.

Model architectureSentiment Analysisdomain adaptation
0 likes · 14 min read
Federated Transfer Learning: Concepts, Examples, and Model Structures
DataFunTalk
DataFunTalk
Aug 22, 2020 · Artificial Intelligence

Dual Cold-Start News Recommendation via Neighborhood-Based Transfer Learning

This article presents a Neighborhood‑based Transfer Learning approach to solve the Dual Cold‑Start Recommendation problem in news services by transferring app‑installation similarity knowledge and using category‑level preferences to recommend unseen articles to brand‑new users.

AIcold startneighborhood
0 likes · 8 min read
Dual Cold-Start News Recommendation via Neighborhood-Based Transfer Learning
Ctrip Technology
Ctrip Technology
Jun 4, 2020 · Artificial Intelligence

Semantic Matching Models for Travel QA: Deep Learning Techniques, Interaction Models, and Transfer Learning

This article reviews the evolution of semantic matching models for travel question‑answering, covering traditional keyword and probabilistic methods, deep‑learning encoders such as LSTM, CNN, and Transformer, interaction‑based architectures like MatchPyramid and hCNN, as well as transfer‑learning and multilingual extensions to improve practical deployment.

context modelingdeep learningnatural language processing
0 likes · 21 min read
Semantic Matching Models for Travel QA: Deep Learning Techniques, Interaction Models, and Transfer Learning
DataFunTalk
DataFunTalk
May 29, 2020 · Artificial Intelligence

Model‑Independent Learning: Multi‑Task Learning and Transfer Learning

This article explains two model‑independent learning paradigms—multi‑task learning and transfer learning—detailing their motivations, sharing mechanisms, training procedures, theoretical formulations, and practical benefits such as improved generalization, data efficiency, and domain‑invariant representations.

Machine Learningdeep learningdomain adaptation
0 likes · 21 min read
Model‑Independent Learning: Multi‑Task Learning and Transfer Learning
DataFunTalk
DataFunTalk
Apr 16, 2020 · Artificial Intelligence

Comprehensive Survey of Pre-trained Models for Natural Language Processing

This article provides a detailed survey of pre‑trained models (PTMs) for natural language processing, classifying them into shallow embeddings and contextual encoders, discussing training paradigms such as knowledge integration and model compression, and offering guidance on transfer learning and future challenges.

Model Compressionknowledge integrationnatural language processing
0 likes · 25 min read
Comprehensive Survey of Pre-trained Models for Natural Language Processing
DataFunTalk
DataFunTalk
Mar 17, 2020 · Artificial Intelligence

A Survey of Text Data Augmentation Techniques in Natural Language Processing

This article systematically reviews recent developments in text data augmentation for natural language processing, covering common scenarios such as low‑resource and imbalanced classification, and detailing five major techniques—including back‑translation, EDA, TF‑IDF‑based replacement, contextual augmentation, and language‑model‑based methods—with experimental results and future directions.

Machine LearningNLPdata augmentation
0 likes · 27 min read
A Survey of Text Data Augmentation Techniques in Natural Language Processing
Tencent Cloud Developer
Tencent Cloud Developer
Jan 14, 2020 · Artificial Intelligence

MedicalNet: Tencent's Pre-trained Model for 3D Medical Imaging AI

MedicalNet, Tencent’s open-source framework, aggregates diverse small 3D medical imaging datasets into a large pre-training corpus, applies dataset filtering and joint spatial-pixel normalization, and provides encoder-decoder models that accelerate convergence and boost accuracy for AI-driven diagnosis in data-scarce medical imaging scenarios.

3D Medical ImagingHealthcare AIMedicalNet
0 likes · 5 min read
MedicalNet: Tencent's Pre-trained Model for 3D Medical Imaging AI
DataFunTalk
DataFunTalk
Oct 9, 2019 · Artificial Intelligence

Multilingual Content Understanding in UC International Feed Recommendation

This article presents a comprehensive overview of the challenges, requirements, and technical solutions for multilingual content understanding in UC's international information‑flow recommendation system, covering structured signal construction, low‑resource NLP techniques, transfer learning, quality modeling, and image‑based signal integration.

NLPRecommendation Systemscontent understanding
0 likes · 14 min read
Multilingual Content Understanding in UC International Feed Recommendation
DataFunTalk
DataFunTalk
May 29, 2019 · Artificial Intelligence

General‑Domain Conversational QA: Technologies, Challenges, and Alibaba UC’s Practice

This article reviews the evolution, architecture, and key technical challenges of general‑domain conversational QA systems, describing Alibaba UC’s search background, dialogue bot types, data pipelines, and advanced methods such as transfer learning, few‑shot learning, and multi‑dimensional dialogue management.

AlibabaDialogue SystemsNLP
0 likes · 12 min read
General‑Domain Conversational QA: Technologies, Challenges, and Alibaba UC’s Practice
Didi Tech
Didi Tech
Mar 28, 2019 · Artificial Intelligence

Overview of the CVPR 2019 WAD Autonomous Driving Challenge and Participation Details

The CVPR 2019 WAD Autonomous Driving Challenge, hosted in Long Beach, introduces four new tasks—including object‑detection and tracking transfer‑learning tracks using Didi’s massive D²‑City and Berkeley’s BDD100K datasets, plus a large‑scale detection interpolation track—aimed at advancing vision algorithms under diverse, difficult driving conditions, with global teams invited to register by May 31 and winners announced at the workshop on June 17.

AIchallengecomputer vision
0 likes · 6 min read
Overview of the CVPR 2019 WAD Autonomous Driving Challenge and Participation Details
Hulu Beijing
Hulu Beijing
Mar 26, 2019 · Artificial Intelligence

Meta-Learning Explained: Core Concepts, Scenarios, and Few-Shot Learning Benefits

This article introduces meta‑learning (learning to learn), its historical roots, explains why it excels in small‑sample and multi‑task settings, contrasts it with supervised and reinforcement learning, and outlines the theoretical reasons it enables rapid few‑shot adaptation.

Machine Learningfew-shot learningmeta-learning
0 likes · 8 min read
Meta-Learning Explained: Core Concepts, Scenarios, and Few-Shot Learning Benefits
Tencent Cloud Developer
Tencent Cloud Developer
Feb 15, 2019 · Artificial Intelligence

Trends and Challenges in Artificial Intelligence: Data Security, Deployment Bottlenecks, and Transfer Learning

The article reviews China's AI progress and lingering gaps, highlights data‑security regulations and deployment bottlenecks caused by siloed “small data,” champions transfer learning as a solution for limited data, dispels AI‑cold‑war and job‑loss myths, and forecasts continued growth through secure, collaborative, and efficient AI deployment.

AI trendsArtificial IntelligenceData Security
0 likes · 13 min read
Trends and Challenges in Artificial Intelligence: Data Security, Deployment Bottlenecks, and Transfer Learning
Youku Technology
Youku Technology
Oct 25, 2018 · Artificial Intelligence

Interview with Wang Xiaobo (Yongshu) on Large‑Scale Machine Learning, Recommendation Systems, and AutoML at Alibaba and Youku

At the AI Pioneer Conference, Wang Xiaobo, head of Alibaba’s Commercial Machine Intelligence and Youku’s algorithm teams, discussed large‑scale distributed learning, recommendation challenges such as cold‑start and video heterogeneity, AutoML innovations, multi‑modal search during promotions, and the future demand for specialists in few‑shot learning and domain adaptation.

AutoMLLarge-Scale Distributed Learningcold start
0 likes · 21 min read
Interview with Wang Xiaobo (Yongshu) on Large‑Scale Machine Learning, Recommendation Systems, and AutoML at Alibaba and Youku
Qizhuo Club
Qizhuo Club
Jul 30, 2018 · Artificial Intelligence

Mastering Inception v3: From Codebase to Rose Recognition with TensorFlow

This article walks through the Inception v3 TensorFlow codebase, explains its design principles, details the training script flags and loss calculations, shows how to fine‑tune the model on a flower dataset, and provides practical tips for building custom datasets and optimizing hyper‑parameters for image classification.

CNNImage ClassificationInception
0 likes · 25 min read
Mastering Inception v3: From Codebase to Rose Recognition with TensorFlow
Meituan Technology Team
Meituan Technology Team
Jul 12, 2018 · Artificial Intelligence

AI-Powered Image Moderation at Meituan: Watermark Detection, Celebrity Face Recognition, and Content Filtering

Meituan employs AI-driven image moderation across millions of daily uploads, using an SSD‑ResNet detector for watermarks, a multi‑scale Faster R‑CNN ensemble for celebrity faces, a CNN‑based pornographic classifier with incremental learning, and transfer‑learned scene classification, while routing uncertain cases to human reviewers.

Image Moderationcontent filteringdeep learning
0 likes · 19 min read
AI-Powered Image Moderation at Meituan: Watermark Detection, Celebrity Face Recognition, and Content Filtering
Baobao Algorithm Notes
Baobao Algorithm Notes
Jun 30, 2018 · Artificial Intelligence

Winning Kaggle’s Avito Demand Prediction with Multi‑Source Neural Nets and Transfer Learning

This article breaks down the Avito demand‑prediction Kaggle competition, detailing the data mix of text, images, structured fields and time series, the layered feature‑engineering tactics, multi‑source heterogeneous neural network designs, and a transfer‑learning trick that propelled the top solutions.

AvitoKaggleMulti-Source Learning
0 likes · 11 min read
Winning Kaggle’s Avito Demand Prediction with Multi‑Source Neural Nets and Transfer Learning
JD Retail Technology
JD Retail Technology
Jun 13, 2018 · Artificial Intelligence

IJCAI 2018 International Advertising Algorithm Competition Champion Uses Transfer Learning and LightGBM for Ad Conversion Prediction

The IJCAI 2018 International Advertising Algorithm Competition was won by JD.com algorithm engineer Hua Zhixiang, who employed a two‑stage LightGBM model with transfer learning and carefully designed statistical, temporal, ranking, and representation features to achieve top conversion‑rate predictions on massive e‑commerce advertising data.

AdvertisingIJCAILightGBM
0 likes · 5 min read
IJCAI 2018 International Advertising Algorithm Competition Champion Uses Transfer Learning and LightGBM for Ad Conversion Prediction
Alibaba Cloud Developer
Alibaba Cloud Developer
Feb 5, 2018 · Artificial Intelligence

How Alibaba’s AliMe Evolved in 2017: AI Architecture, Algorithms, and Real‑World Impact

In 2017 Alibaba's AliMe chatbot platform expanded from a single‑company solution to a multilingual, multi‑channel AI service, introducing platform‑level SaaS/PaaS capabilities, a seven‑layer front‑end architecture, modular back‑end design, advanced intent recognition, knowledge‑graph‑driven product management, reinforcement‑learning‑based recommendation, and machine‑reading comprehension for enterprise and consumer use cases.

AI PlatformAlibabaChatbot
0 likes · 23 min read
How Alibaba’s AliMe Evolved in 2017: AI Architecture, Algorithms, and Real‑World Impact
AntTech
AntTech
Dec 22, 2017 · Artificial Intelligence

Transfer Learning: Concepts, Challenges, and Recent Research Highlights from CIKM 2017

This article reviews the key concepts, challenges, and recent research on transfer learning presented at CIKM 2017, covering instance, feature, parameter, and relation‑based methods, supervised and unsupervised deep TL approaches, and transitive transfer learning with associated loss formulations and optimization strategies.

AI researchMachine Learningdeep learning
0 likes · 9 min read
Transfer Learning: Concepts, Challenges, and Recent Research Highlights from CIKM 2017
21CTO
21CTO
Oct 9, 2017 · Artificial Intelligence

How Wukong’s AI Porn Detection System Achieves 99.5% Accuracy

This article explains the challenges of image‑based porn detection, details the multi‑label classification approach of the Wukong system, and reveals the deep‑learning techniques—including CNN evolution, transfer learning, loss functions, adversarial training, and GAN‑based data augmentation—that enable over 99.5% accuracy with massive daily request volumes.

CNNGaNImage Classification
0 likes · 18 min read
How Wukong’s AI Porn Detection System Achieves 99.5% Accuracy
Efficient Ops
Efficient Ops
Aug 9, 2017 · Artificial Intelligence

Can AI Predict Disk Failures? RGF + Transfer Learning for Reliable Data Centers

This article reviews a KDD 2016 study that combines the Regularized Greedy Forest algorithm with transfer learning to accurately predict hard‑disk failures in data centers, addressing challenges like irrelevant SMART attributes, imbalanced data, and model portability across disk models.

Machine LearningRGF algorithmSMART attributes
0 likes · 12 min read
Can AI Predict Disk Failures? RGF + Transfer Learning for Reliable Data Centers
Ctrip Technology
Ctrip Technology
Jan 22, 2017 · Artificial Intelligence

Cross-Domain Recommendation: Concepts, Methods, and Novel Approaches

This article reviews the fundamentals of cross-domain recommendation, explains the limitations of single‑domain personalized recommendation, surveys existing collaborative‑filtering, transfer‑learning, and knowledge‑based methods, and introduces two novel tensor‑factorization and bilinear multilevel models that achieve superior performance on real datasets.

Machine Learningcollaborative filteringcross-domain recommendation
0 likes · 17 min read
Cross-Domain Recommendation: Concepts, Methods, and Novel Approaches