# adv_rmd

**Repository Path**: NoaRicky/adv_rmd

## Basic Information

- **Project Name**: adv_rmd
- **Description**: The adversarial training for sequential recommendation system
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-05-18
- **Last Updated**: 2020-12-29

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Adversarial Training for Sequential Recommendation

This is the project repository for paper

## Project Structure

- notebooks: jupyter notebook files for project code draft
- models: all models used in project
- utils: contains metric, trainer for experiment
- inputs
  - raw: store raw data
  - process: store process data in csv format
- datasets:
  - creators:
  - datasets:
  - collectors:
  - processors:

## Models

### [RRN](http://alexbeutel.com/papers/rrn_wsdm2017.pdf)

#### RRN-Propagate

- embbedding layers for user and items
- lstm layers for dynamic embbedding
- rating emission by static embedding and dynamic embedding

$$\hat{r}_{ij|t} = f(u_{it},m_{jt},u_i,m_j) := $$