RecSys ’18: Generation Meets Recommendation: Proposing Novel Items for Groups of Users

Original article was published on Deep Learning on Medium

RecSys ’18: Generation Meets Recommendation: Proposing Novel Items for Groups of Users

Recommendation system paper challenge (16/50)

https://www.pinterest.com/pin/736338607813281340/

paper link

What problem do they solve?

They want to generate a new item to user group

What is the model they propose?

They utilized VAE model (Variational Autoencoder), which is popular in computer vision and NLP.

The basic idea is find encoder and decoder with objective function and use decoder to find out the novel item.

The following formula is their objective function (Loss function) .

They also use linear encoder and decoder to be baseline model.

Linear Encoding and Decoding

Their overall loss function:

Note: here they only consider binary target value. (Y/F) (Click / Non-Click)

So that they employ sigmoid function to transfer dot product value to [0, 1]

Their rating loss function:

Their reconstruction loss function:

It is naively to compare reconstructed feature vector and real feature vector.

In computer vision, it is comparing reconstructed pixel with original pixel.

So finally the loss function is below:

Nonlinear Encoding and Decoding with Deep Generative Modeling

There is a key difference is the VAE is derived under a probabilistic framework.

Therefore, their objective function is a little different.

However, it is hard to compute it. So they perform approximate inference by maximizing the variational or evidence lower bound (ELBO).

where

First term is rating loss function.

Second term is reconstructing loss function

Third represents KL divergence, which penalize the difference between p_z_i and q_phi

Generating new item (greedy)

Their goal is to find novel items that possess maximum coverage with maximum aggregate rating, but it is NP-hard problem.

Hence, they applied greedy algorithm to do the search.

They pick the candidate item that attains the maximum total rating given by uncovered users until K samples are selected.

Result

VAE has less RMSE (outperform than LM model in prediction rating)

Besides that, the new item generated from VAE has less RMSE than real item (nearest item)

They can really generate a new item which does not exist in the database

My review:

Since I did several VAE and GAN projects before, I feel like the generated image is not clear. It is better to use 1 additional GAN module to make the generated image close to real image.

Other related blogs:

Beyond Clicks: Dwell Time for Personalization

RecSys16: Adaptive, Personalized Diversity for Visual Discovery

RecSys ’16: Local Item-Item Models for Top-N Recommendation

NAACL’19: Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence

RecSys ’17: Translation-based Recommendation

RecSys ’17: Modeling the Assimilation-Contrast Effects in Online Product Rating Systems: Debiasing and Recommendations

RecSys ’18: HOP-Rec: High-Order Proximity for Implicit Recommendation

RecSys ’18: Impact of item consumption on assessment of recommendations in user studies

Best paper in RecSys:

https://recsys.acm.org/best-papers/

My Website:

https://light0617.github.io/#/