CS 707 Data and Web Science Seminar (HWS 2018)

The Data and Web Science seminar covers recent topics in data and web science. This term, the seminar focuses on Generative Neural Networks.

Organization

  • This seminar is organized by Yanjie Wang , Prof. Dr. Margret Keuper, and Prof. Dr. Rainer Gemulla
  • Available for Master students (2 SWS, 4 ECTS. If you are a Bachelor student and want to take this seminar (2 SWS, 5 ECTS), please contact Prof. Gemulla.
  • Prerequisites: solid background in data analytics and machine learning; courses like Data Mining and Matrices / Hot Topics in Machine Learning / High Level Computer Vision are recommended

Goals

In this seminar, you will

  • read recent papers on generative models
  • understand the paper assigned to you
  • give a flash presentation about this paper
  • give a technical presentation about this paper
  • summarize the paper, its background, and related work in a 8-10 pages report 

Schedule

  • Register as described below.
  • Attend the kickoff meeting on Sep 07 (tentative).
  • Work individually throughout the semester: explore relevant literature;  write a report; give a 3-minute flash presentation on your topic; give a 15-minute presentation on your topic.
  • Meet your advisor for guidance and feedback.
  • For more information, have a look at the schedule.

Reistration and Topics

Explore the list of topics below and select at least 3 topics of your preference. Register via Portal2 before Aug.29. If you are accepted into the seminar, please provide your preferred topics until Sep 06 via ywang(at)uni-mannheim.deemail to Yanjie Wang. The actual topic assignment takes place soon afterwards; we will notify you via email. Our goal is to assign to you to one of your preferred topics.

In addition to the topics listed below, you are free so suggest alternative topics in the area of the seminar.

 

1. f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

Sebastian Nowozin et al.

NIPS 2016

 

2. Auto-Encoding Variational Bayes

Diederik P. Kingma et al.

ICLR 2014

 

3. Generative Adversarial Nets

Ian J. Goodfellow et al.

NIPS 2014

 

4. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Jun-Yan Zhu et al.

 CVPR 2017

 

5. A Variational U-Net for Conditional Appearance and Shape Generation

Patrick Esser et al.

CVPR 2018

 

6. Least Squares Generative Adversarial Networks

Xudong Mao et al.

ICCV 2017

 

7. Wasserstein GAN

Martin Arjovsky et al.

 arxiv 2017 

8. Energy-based Generative Adversarial Nets

Junbo Zhao et al.

ICLR 2017

 

9. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Xi Chen et al.

NIPS 2016

 

10. Autoencoding beyond pixels using a learned similarity metric

Anders Boesen Lindbo Larsen et al.

ICML 2016

 

11. Generative Moment Matching Networks

Yujia Li et al.

 ICML 2015

 

12. Learning What and Where to Draw

 Scott Reed et al.

NIPS 2016

Giving talks / writing reports

  • "Giving conference talks", by Prof. Dr. Rainer Gemulla [pdf]
  • "Writing for Computer Science" by Justin Zobel