# Generating Multi-type Temporal Sequences to Mitigate Class-imbalanced Problem

arXiv: https://arxiv.org/abs/2104.03428 · HTML: https://mlsanity.com/paper/2104.03428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models](https://mlsanity.com/paper/1705.10843/) (2017)
- [GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution](https://mlsanity.com/paper/1611.04051/) (2016)
- [Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics](https://mlsanity.com/paper/2001.00449/) (2020)
- [Deep Neural Networks for Bot Detection](https://mlsanity.com/paper/1802.04289/) (2018)
- [One-Class Adversarial Nets for Fraud Detection](https://mlsanity.com/paper/1803.01798/) (2018)
- [Generating and designing DNA with deep generative models](https://mlsanity.com/paper/1712.06148/) (2017)
- [Prescribed Generative Adversarial Networks](https://mlsanity.com/paper/1910.04302/) (2019)
- [On the Evaluation of Conditional GANs](https://mlsanity.com/paper/1907.08175/) (2019)
- [Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks](https://mlsanity.com/paper/1907.03355/) (2019)
- [Clicktok: Click Fraud Detection using Traffic Analysis](https://mlsanity.com/paper/1903.00733/) (2019)

## Abstract (arXiv)

From the ad network standpoint, a user's activity is a multi-type sequence of temporal events consisting of event types and time intervals. Understanding user patterns in ad networks has received increasing attention from the machine learning community. Particularly, the problems of fraud detection, Conversion Rate (CVR), and Click-Through Rate (CTR) prediction are of interest. However, the class imbalance between major and minor classes in these tasks can bias a machine learning model leading to poor performance. This study proposes using two multi-type (continuous and discrete) training approaches for GANs to deal with the limitations of traditional GANs in passing the gradient updates for discrete tokens. First, we used the Reinforcement Learning (RL)-based training approach and then, an approximation of the multinomial distribution parameterized in terms of the softmax function (Gumble-Softmax). Our extensive experiments based on synthetic data have shown the trained generator can generate sequences with desired properties measured by multiple criteria.