SlideShare ist ein Scribd-Unternehmen logo
1 von 36
DM
Deep Learning based Recommender System :
A survey and New Perspectives (1/2)
Zhang Et al. ’17
이현성
DMIndex
Introduction
Category of neural network and NN based recommender algorithms
MLP-based recommenders
AE-based recommenders
CNN-based recommenders
RNN-based recommenders
DSSM-based recommendersa
DM
Introduction
DM
Why should we care about deep learning based RS?
many successes in various application areas in both academia and industry.
Deep Learning techniques enables to exploit complex data
image, tags, text,
DM
이 논문이 너무 많은 모델을 다루고 있어서
모델의 성능이나, 자세한 알고리즘은 제외하고
Deep Learning 모델을 사용한 이유
이런 점을 Deep Learning을 이용해 해결하려 했다
같은 Motivation과 Insight만 note하겠습니다.
DM
Category of neural network and NN based r
ecommender algorithms
DM
Frequently used Deep Learning Techniques
• Multi-Layer Perceptron (MLP)
• Autoencoder (AE)
• Convolutional Neural Network (CNN)
• Recurrent Neural Network (RNN)
• Deep Semantic Similarity Model (DSSM)
• Restricted Boltzmann Machine (RBM)
• Neural Autoregressive Distribution Estimation (NADE)
• Generative Adversarial Network (GAN)
DM
Recommender systems as neural network models
1) Models Using Single Deep-Learning Techniques
a) exploit one of mentioned eight techniques
i) Extracting item features from images
ii) Recommendation with explanations
2) Composite Models
a) exploit more than one deep learning techniques
i) GAN using AE as generator, MLP as discriminator.
ii) applying extracted item features using CNN to RNN
DM
Integration of Deep learning with Traditional RS
1) Solely Deep-Learning based Models
a) Predicting scores using MLP
1) Coupled Models (Recommender model + Neural network model)
a) AutoEncoder + extracted image features with CNN
i) two model objectives are updated simultaneously (Tightly Coupled models)
ii) two step learning (Loosely Coupled models )
DM
Classification of Deep-Learning based Recommender System
DM
MLP Based Recommender Systems
DMNeural Collaborative Filtering (NCF)
 Motivation
 Previous Matrix Factorization only consi
ders linear relationship between users a
nd items
 𝑦 𝑢𝑖 = 𝑑𝑜𝑡 𝑢, 𝑖
 Solution
 Non-linear Relationship between users
and items
 𝑦 𝑢𝑖 = 𝑓 𝑢, 𝑖 Θ
 Where 𝑓 Θ is multi-layer perceptron.
 User-Item interaction prediction
DMWide & Deep Learning
Motivation
 Linear regression is good at
memorization
 Deep MLP is good at generalization,
catching deep features.
Solution
 Integrate linear regression and MLP
구글 플레이스토어에서, 쿼리에 맞
는 application하는 데 사용 중인
알고리즘
DMYoutube Video Recommendation (Covington et al.)
Motivation
 There are too many features to tuned
Solution
 MLP works quite well without
exhaustive feature engineering
Youtube에서 personalized video
recommendation을 할 때 사용중
인 알고리즘
DM
Autoencoder Based Recommender Systems
DM추천 시스템에서 Autoencoder가 주로 사용되는 용
도
Predict interaction between user
and items
Motivation
 Denosing, Reconstruction effects of
Autoencoder will be helpful in
revealing un-observed preferences of
users.
Feature Extraction
Motivation
 Use Autoencoder to learn low-
dimension representation in the
bottleneck layer
Autoencoder는 주로 이 두 가지 방법으로 사용되고, IR과 Recsys
community에서는 상당히 기본적인 방법이 되었다.
DMOverview
DMAutoencoder as generative model
3
5
4
i1 i2 i3 i4 i5
u1 ? ? 3 4 ?
u2 2 ? 5 ? ?
u3 ? 1 ? ? ?
u4 2 ? 4 ? 3
2.8
4.6
2.3
3.5
Predicted rating 𝑟33
Rating prediction
DMAutoencoder as feature extractor
1
0
1
0
animation Horror Action romance
i1
i2 1 0 0 1
i3
i4
0.1
0.8
1
0
0
1
Predicted rating 𝑟33
Low-dimension
representation
DM
CNN Based Recommender Systems
DMConvolutional Neural Network is
Capable to extract low-dimensional feature from complex data
(image, fixed-size sequences…)
These side information(image) can be used to alleviate cold-start
problem.
Motivation
 CNN-based recommender systems mainly aims to help recommendation quality
using side information
DMGeneral CNN based Recommender systems
Motivation
 Images of items contains much
information
Solution
 Use CNN to extract these information
into latent codes.
Image of item i
CNN
Latent code
Item vector of
item i
Output : Item representation
Addition
DM
Personalized Image Tag Recommendation
(Nguyen et al.)
Motivation
 CNN can code image into vectors
 User can be embed into vectors
using current ML techniques.
Image에 어울리는 tag를 generate
하기 위해 제안된 알고리즘
Image input
Convolution
Max-pooling User info
Tag Food Holid
ay
Love … Selfie
Score 0.3 0.1 0.5 … 0.8
Image에서 feature를 미리
추출해서 pretrained vector로
사용하는 경우도 많다.
DMCNN for Audio Feature Extraction
Motivation
 Allivate cold-start problem using
Content information
Solution
 Learn latent vector representation
using Audio features
Audio Features for item i
Convolution
𝑦𝑖′ 𝑦𝑖
𝑦𝑖 는 WMF model이 만든 item i의 latent
representation
DM
RNN Based Recommender Systems
DMRecurrent Neural Network
Mainly concerned with sequential behaviors
User/Item evolves with time (temporal dynamics)
Session based recommendations
 rare user information is known
 Sequential behavior become more important than normal cases.
Text understanding
 Like CNN, RNN enables to exploit rich side information(text)
DMGRU-Rec (Hidasi et al.)
Motivation
 user’s each click in web-page is
closely related with each others
Solution
 Bidirectional GRU fits to model this
sequential behavior well
Input :
One-
hot
Enco
ded
Vect
or
Emb
eddin
g
Layer
GRU
Layer
GRU
Layer
GRU
Layer
…
Feed
forwa
rd
Layer
Outp
ut :
score
s on
items
DMRecurrent Recommender Network (Wu et al.)
Motivation
 Users and items behavior change
over time
Solution
 Models user and item behaviors
using LSTM
 𝒓 𝒖𝒊|𝒕 = 𝒇 𝒖 𝒖, 𝒖 𝒖𝒕, 𝒗𝒊, 𝒗𝒊𝒕
DMGRU Multitask Learning (Bansal et al.)
Motivation
 Rich text information will be helpful
Solution
 Use GRU to encode text sequences
(review, description of items)
Text description
of item i
GRU
Latent code
Item vector of
item i
Output : Item representation
Addition
여러 representation을 합칠 때,
의외로 dot이나 elementwise
multiplication보다 단순 addition이
성능이 더 좋은 경우가 많은 것 같다.
DM
DSSM Based Recommender Systems
DMDeep Structured Semantic Model
DMDeep Structured Semantic Model
DMTraining DSSM
Query와 relevant한 document의
cosine similarity는 1에 가깝게,
Query와 irrevant한 document의
cosine similarity는 0에 가깝게.
DMDeep Structured Semantic Model
Motivation
 User,item 둘 다 side-information을 갖
고 있다.
Solution
 DSSM을 그대로 적용하자.
 DSSM 자체는 similarity measure를
제외하면 Neural Collaborative
filtering, 혹은 MF with side
information의 generalization으로 볼
수 있다.
Query가 아닌 user의
information을 input으로
DMFuture research directions
Better understanding of users and items
 딥러닝 모델은 이미지나 텍스트를 잘 모델링한다!(적어도 기존의 방법보다는) 하지만
이러한 모델링은 아직 미숙한 수준이며(Deep learning에서 이용되는 아이디어를 그대
로 가져온 수준), 더 잘 하는 방법이 있을 것이다.
Temporal Dynamics
 Session based Recommendation systems, and recommender with temporal
dynamics are not novel research topics, but they are largely underinvestiagted.
DMFuture research directions
Cross-domain / Multi-task learning
 User의 purchase behavior 등을 은행 등에서 활용하려는 시도가 있다.
 한 도메인의 knowledge을, 다른 도메인에 적용하거나,
 여러 도메인의 지식을 동시에 활용했을 시의 성능 향상을 기대할 수 있다.
Novel Evaluation Metrics
 Accuracy, Relevance measures are not good for evaluating recommender.

Weitere ähnliche Inhalte

Was ist angesagt?

Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
Kishor Datta Gupta
 
Recommender system introduction
Recommender system   introductionRecommender system   introduction
Recommender system introduction
Liang Xiang
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at Netflix
Justin Basilico
 
Recommender system algorithm and architecture
Recommender system algorithm and architectureRecommender system algorithm and architecture
Recommender system algorithm and architecture
Liang Xiang
 

Was ist angesagt? (20)

Deep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender Systems
 
Personalized Page Generation for Browsing Recommendations
Personalized Page Generation for Browsing RecommendationsPersonalized Page Generation for Browsing Recommendations
Personalized Page Generation for Browsing Recommendations
 
Recent advances in deep recommender systems
Recent advances in deep recommender systemsRecent advances in deep recommender systems
Recent advances in deep recommender systems
 
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...
 
Collaborative Filtering using KNN
Collaborative Filtering using KNNCollaborative Filtering using KNN
Collaborative Filtering using KNN
 
Recommender system introduction
Recommender system   introductionRecommender system   introduction
Recommender system introduction
 
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
 
[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systems[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systems
 
Introduction to Recommendation Systems
Introduction to Recommendation SystemsIntroduction to Recommendation Systems
Introduction to Recommendation Systems
 
Challenges and Solutions in Group Recommender Systems
Challenges and Solutions in Group Recommender SystemsChallenges and Solutions in Group Recommender Systems
Challenges and Solutions in Group Recommender Systems
 
Recommendation System
Recommendation SystemRecommendation System
Recommendation System
 
Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial
 
Collaborative Filtering and Recommender Systems By Navisro Analytics
Collaborative Filtering and Recommender Systems By Navisro AnalyticsCollaborative Filtering and Recommender Systems By Navisro Analytics
Collaborative Filtering and Recommender Systems By Navisro Analytics
 
Talk@rmit 09112017
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017
 
Movie lens recommender systems
Movie lens recommender systemsMovie lens recommender systems
Movie lens recommender systems
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
Project presentation
Project presentationProject presentation
Project presentation
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at Netflix
 
Recommender system algorithm and architecture
Recommender system algorithm and architectureRecommender system algorithm and architecture
Recommender system algorithm and architecture
 
Past, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectivePast, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspective
 

Ähnlich wie Deep learning based recommender systems (lab seminar paper review)

Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence
CruzIbarra161
 

Ähnlich wie Deep learning based recommender systems (lab seminar paper review) (20)

From Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptxFrom Conventional Machine Learning to Deep Learning and Beyond.pptx
From Conventional Machine Learning to Deep Learning and Beyond.pptx
 
Bangla Handwritten Digit Recognition Report.pdf
Bangla Handwritten Digit Recognition  Report.pdfBangla Handwritten Digit Recognition  Report.pdf
Bangla Handwritten Digit Recognition Report.pdf
 
Three classes of deep learning networks
Three classes of deep learning networksThree classes of deep learning networks
Three classes of deep learning networks
 
Occurrence Prediction_NLP
Occurrence Prediction_NLPOccurrence Prediction_NLP
Occurrence Prediction_NLP
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Top 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know in
 
presentation.ppt
presentation.pptpresentation.ppt
presentation.ppt
 
AI & ML in Defence Systems - Sunil Chomal
AI & ML in Defence Systems   - Sunil ChomalAI & ML in Defence Systems   - Sunil Chomal
AI & ML in Defence Systems - Sunil Chomal
 
Archana kalapgar 19210184_ca684
Archana kalapgar 19210184_ca684Archana kalapgar 19210184_ca684
Archana kalapgar 19210184_ca684
 
One shot learning
One shot learningOne shot learning
One shot learning
 
Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence
 
Tejal nijai 19210412_report
Tejal nijai 19210412_reportTejal nijai 19210412_report
Tejal nijai 19210412_report
 
Machine learning-for-dummies-andrews-sobral-activeeon
Machine learning-for-dummies-andrews-sobral-activeeonMachine learning-for-dummies-andrews-sobral-activeeon
Machine learning-for-dummies-andrews-sobral-activeeon
 
deeplearning
deeplearningdeeplearning
deeplearning
 
Machine Learning for Dummies (without mathematics)
Machine Learning for Dummies (without mathematics)Machine Learning for Dummies (without mathematics)
Machine Learning for Dummies (without mathematics)
 
Building Azure Machine Learning Models
Building Azure Machine Learning ModelsBuilding Azure Machine Learning Models
Building Azure Machine Learning Models
 
ML crash course
ML crash courseML crash course
ML crash course
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.ppt
 
SVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR ImageSVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR Image
 
Muhammad Usman Akhtar | Ph.D Scholar | Wuhan University | School of Co...
Muhammad Usman Akhtar  |  Ph.D Scholar  |  Wuhan  University  |  School of Co...Muhammad Usman Akhtar  |  Ph.D Scholar  |  Wuhan  University  |  School of Co...
Muhammad Usman Akhtar | Ph.D Scholar | Wuhan University | School of Co...
 

Mehr von hyunsung lee

2013313990 이현성 졸업작품 제안서
2013313990 이현성 졸업작품 제안서2013313990 이현성 졸업작품 제안서
2013313990 이현성 졸업작품 제안서
hyunsung lee
 
Derivation of cost function for logistic regression
Derivation of cost function for logistic regressionDerivation of cost function for logistic regression
Derivation of cost function for logistic regression
hyunsung lee
 

Mehr von hyunsung lee (9)

Learning deep structured semantic models for web search
Learning deep structured semantic models for web searchLearning deep structured semantic models for web search
Learning deep structured semantic models for web search
 
추천 시스템 개요 (1)-draft
추천 시스템 개요 (1)-draft추천 시스템 개요 (1)-draft
추천 시스템 개요 (1)-draft
 
Catching co occurrence information using word2vec-inspired matrix factorization
Catching co occurrence information using word2vec-inspired matrix factorizationCatching co occurrence information using word2vec-inspired matrix factorization
Catching co occurrence information using word2vec-inspired matrix factorization
 
아이템 추천의 다양성을 높이기 위한 후처리 방법(논문 리뷰)
아이템 추천의 다양성을 높이기 위한 후처리 방법(논문 리뷰)아이템 추천의 다양성을 높이기 위한 후처리 방법(논문 리뷰)
아이템 추천의 다양성을 높이기 위한 후처리 방법(논문 리뷰)
 
Session-Based Recommendations with Recurrent Neural Networks (Balazs Hidasi, ...
Session-Based Recommendations with Recurrent Neural Networks(Balazs Hidasi, ...Session-Based Recommendations with Recurrent Neural Networks(Balazs Hidasi, ...
Session-Based Recommendations with Recurrent Neural Networks (Balazs Hidasi, ...
 
Neural collaborative filtering-발표
Neural collaborative filtering-발표Neural collaborative filtering-발표
Neural collaborative filtering-발표
 
Word vectorization(embedding) with nnlm
Word vectorization(embedding) with nnlmWord vectorization(embedding) with nnlm
Word vectorization(embedding) with nnlm
 
2013313990 이현성 졸업작품 제안서
2013313990 이현성 졸업작품 제안서2013313990 이현성 졸업작품 제안서
2013313990 이현성 졸업작품 제안서
 
Derivation of cost function for logistic regression
Derivation of cost function for logistic regressionDerivation of cost function for logistic regression
Derivation of cost function for logistic regression
 

Kürzlich hochgeladen

Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Bertram Ludäscher
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
vexqp
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit RiyadhCytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
Abortion pills in Riyadh +966572737505 get cytotec
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
ZurliaSoop
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
gajnagarg
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
Health
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
gajnagarg
 

Kürzlich hochgeladen (20)

Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
 
SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
SR-101-01012024-EN.docx  Federal Constitution  of the Swiss ConfederationSR-101-01012024-EN.docx  Federal Constitution  of the Swiss Confederation
SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
 
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptxThe-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
 
Harnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptxHarnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptx
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
 
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With OrangePredicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
Predicting HDB Resale Prices - Conducting Linear Regression Analysis With Orange
 
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit RiyadhCytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
Cytotec in Jeddah+966572737505) get unwanted pregnancy kit Riyadh
 
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24  Building Real-Time Pipelines With FLaNKDATA SUMMIT 24  Building Real-Time Pipelines With FLaNK
DATA SUMMIT 24 Building Real-Time Pipelines With FLaNK
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
 
Sequential and reinforcement learning for demand side management by Margaux B...
Sequential and reinforcement learning for demand side management by Margaux B...Sequential and reinforcement learning for demand side management by Margaux B...
Sequential and reinforcement learning for demand side management by Margaux B...
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
 
Capstone in Interprofessional Informatic // IMPACT OF COVID 19 ON EDUCATION
Capstone in Interprofessional Informatic  // IMPACT OF COVID 19 ON EDUCATIONCapstone in Interprofessional Informatic  // IMPACT OF COVID 19 ON EDUCATION
Capstone in Interprofessional Informatic // IMPACT OF COVID 19 ON EDUCATION
 

Deep learning based recommender systems (lab seminar paper review)

  • 1. DM Deep Learning based Recommender System : A survey and New Perspectives (1/2) Zhang Et al. ’17 이현성
  • 2. DMIndex Introduction Category of neural network and NN based recommender algorithms MLP-based recommenders AE-based recommenders CNN-based recommenders RNN-based recommenders DSSM-based recommendersa
  • 4. DM Why should we care about deep learning based RS? many successes in various application areas in both academia and industry. Deep Learning techniques enables to exploit complex data image, tags, text,
  • 5. DM 이 논문이 너무 많은 모델을 다루고 있어서 모델의 성능이나, 자세한 알고리즘은 제외하고 Deep Learning 모델을 사용한 이유 이런 점을 Deep Learning을 이용해 해결하려 했다 같은 Motivation과 Insight만 note하겠습니다.
  • 6. DM Category of neural network and NN based r ecommender algorithms
  • 7. DM Frequently used Deep Learning Techniques • Multi-Layer Perceptron (MLP) • Autoencoder (AE) • Convolutional Neural Network (CNN) • Recurrent Neural Network (RNN) • Deep Semantic Similarity Model (DSSM) • Restricted Boltzmann Machine (RBM) • Neural Autoregressive Distribution Estimation (NADE) • Generative Adversarial Network (GAN)
  • 8. DM Recommender systems as neural network models 1) Models Using Single Deep-Learning Techniques a) exploit one of mentioned eight techniques i) Extracting item features from images ii) Recommendation with explanations 2) Composite Models a) exploit more than one deep learning techniques i) GAN using AE as generator, MLP as discriminator. ii) applying extracted item features using CNN to RNN
  • 9. DM Integration of Deep learning with Traditional RS 1) Solely Deep-Learning based Models a) Predicting scores using MLP 1) Coupled Models (Recommender model + Neural network model) a) AutoEncoder + extracted image features with CNN i) two model objectives are updated simultaneously (Tightly Coupled models) ii) two step learning (Loosely Coupled models )
  • 10. DM Classification of Deep-Learning based Recommender System
  • 12. DMNeural Collaborative Filtering (NCF)  Motivation  Previous Matrix Factorization only consi ders linear relationship between users a nd items  𝑦 𝑢𝑖 = 𝑑𝑜𝑡 𝑢, 𝑖  Solution  Non-linear Relationship between users and items  𝑦 𝑢𝑖 = 𝑓 𝑢, 𝑖 Θ  Where 𝑓 Θ is multi-layer perceptron.  User-Item interaction prediction
  • 13. DMWide & Deep Learning Motivation  Linear regression is good at memorization  Deep MLP is good at generalization, catching deep features. Solution  Integrate linear regression and MLP 구글 플레이스토어에서, 쿼리에 맞 는 application하는 데 사용 중인 알고리즘
  • 14. DMYoutube Video Recommendation (Covington et al.) Motivation  There are too many features to tuned Solution  MLP works quite well without exhaustive feature engineering Youtube에서 personalized video recommendation을 할 때 사용중 인 알고리즘
  • 16. DM추천 시스템에서 Autoencoder가 주로 사용되는 용 도 Predict interaction between user and items Motivation  Denosing, Reconstruction effects of Autoencoder will be helpful in revealing un-observed preferences of users. Feature Extraction Motivation  Use Autoencoder to learn low- dimension representation in the bottleneck layer Autoencoder는 주로 이 두 가지 방법으로 사용되고, IR과 Recsys community에서는 상당히 기본적인 방법이 되었다.
  • 18. DMAutoencoder as generative model 3 5 4 i1 i2 i3 i4 i5 u1 ? ? 3 4 ? u2 2 ? 5 ? ? u3 ? 1 ? ? ? u4 2 ? 4 ? 3 2.8 4.6 2.3 3.5 Predicted rating 𝑟33 Rating prediction
  • 19. DMAutoencoder as feature extractor 1 0 1 0 animation Horror Action romance i1 i2 1 0 0 1 i3 i4 0.1 0.8 1 0 0 1 Predicted rating 𝑟33 Low-dimension representation
  • 21. DMConvolutional Neural Network is Capable to extract low-dimensional feature from complex data (image, fixed-size sequences…) These side information(image) can be used to alleviate cold-start problem. Motivation  CNN-based recommender systems mainly aims to help recommendation quality using side information
  • 22. DMGeneral CNN based Recommender systems Motivation  Images of items contains much information Solution  Use CNN to extract these information into latent codes. Image of item i CNN Latent code Item vector of item i Output : Item representation Addition
  • 23. DM Personalized Image Tag Recommendation (Nguyen et al.) Motivation  CNN can code image into vectors  User can be embed into vectors using current ML techniques. Image에 어울리는 tag를 generate 하기 위해 제안된 알고리즘 Image input Convolution Max-pooling User info Tag Food Holid ay Love … Selfie Score 0.3 0.1 0.5 … 0.8 Image에서 feature를 미리 추출해서 pretrained vector로 사용하는 경우도 많다.
  • 24. DMCNN for Audio Feature Extraction Motivation  Allivate cold-start problem using Content information Solution  Learn latent vector representation using Audio features Audio Features for item i Convolution 𝑦𝑖′ 𝑦𝑖 𝑦𝑖 는 WMF model이 만든 item i의 latent representation
  • 26. DMRecurrent Neural Network Mainly concerned with sequential behaviors User/Item evolves with time (temporal dynamics) Session based recommendations  rare user information is known  Sequential behavior become more important than normal cases. Text understanding  Like CNN, RNN enables to exploit rich side information(text)
  • 27. DMGRU-Rec (Hidasi et al.) Motivation  user’s each click in web-page is closely related with each others Solution  Bidirectional GRU fits to model this sequential behavior well Input : One- hot Enco ded Vect or Emb eddin g Layer GRU Layer GRU Layer GRU Layer … Feed forwa rd Layer Outp ut : score s on items
  • 28. DMRecurrent Recommender Network (Wu et al.) Motivation  Users and items behavior change over time Solution  Models user and item behaviors using LSTM  𝒓 𝒖𝒊|𝒕 = 𝒇 𝒖 𝒖, 𝒖 𝒖𝒕, 𝒗𝒊, 𝒗𝒊𝒕
  • 29. DMGRU Multitask Learning (Bansal et al.) Motivation  Rich text information will be helpful Solution  Use GRU to encode text sequences (review, description of items) Text description of item i GRU Latent code Item vector of item i Output : Item representation Addition 여러 representation을 합칠 때, 의외로 dot이나 elementwise multiplication보다 단순 addition이 성능이 더 좋은 경우가 많은 것 같다.
  • 33. DMTraining DSSM Query와 relevant한 document의 cosine similarity는 1에 가깝게, Query와 irrevant한 document의 cosine similarity는 0에 가깝게.
  • 34. DMDeep Structured Semantic Model Motivation  User,item 둘 다 side-information을 갖 고 있다. Solution  DSSM을 그대로 적용하자.  DSSM 자체는 similarity measure를 제외하면 Neural Collaborative filtering, 혹은 MF with side information의 generalization으로 볼 수 있다. Query가 아닌 user의 information을 input으로
  • 35. DMFuture research directions Better understanding of users and items  딥러닝 모델은 이미지나 텍스트를 잘 모델링한다!(적어도 기존의 방법보다는) 하지만 이러한 모델링은 아직 미숙한 수준이며(Deep learning에서 이용되는 아이디어를 그대 로 가져온 수준), 더 잘 하는 방법이 있을 것이다. Temporal Dynamics  Session based Recommendation systems, and recommender with temporal dynamics are not novel research topics, but they are largely underinvestiagted.
  • 36. DMFuture research directions Cross-domain / Multi-task learning  User의 purchase behavior 등을 은행 등에서 활용하려는 시도가 있다.  한 도메인의 knowledge을, 다른 도메인에 적용하거나,  여러 도메인의 지식을 동시에 활용했을 시의 성능 향상을 기대할 수 있다. Novel Evaluation Metrics  Accuracy, Relevance measures are not good for evaluating recommender.

Hinweis der Redaktion

  1. 토픽이 너무 많아서, 일단 1-4까지 먼저 Cover하는 것으로 하고, 5,6,7,8은 다음 번에 제가 발표할 때 하도록 할게요…;;;;