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
- 11. DM MLP Based Recommender Systems
- 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
- 15. DM Autoencoder Based Recommender Systems
- 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.
- 17. DMOverview
- 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
- 20. DM CNN Based Recommender Systems
- 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
- 25. DM RNN Based Recommender Systems
- 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.
- 30. DM DSSM Based Recommender Systems
- 31. DMDeep Structured Semantic Model
- 32. DMDeep Structured Semantic Model
- 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.
Editor's Notes
- #8: 토픽이 너무 많아서, 일단 1-4까지 먼저 Cover하는 것으로 하고, 5,6,7,8은 다음 번에 제가 발표할 때 하도록 할게요…;;;;