CS 707 Data and Web Science Seminar (HWS 2017)

The Data and Web Science seminar covers recent topics in data and web science. This term, the seminar focuses on Multi-relational learning.

Goals

Goals

In this seminar, you will

  • Read, understand, and explore scientific literature
  • Summarize a current research topic in a concise report
  • Give two presentations about your topic (one 3 minutes, one 15 minutes)
  • Moderate a scientific discussion about a topic of one of your fellow students
  • Provide feedback to a report and to a presentation of a fellow student

Organization

Schedule

  • Select your preferred topics and register by Sep. 07
  • Attend the kickoff meeting 
  • You will be assigned an adviser, who provides guidance and one-to-one meetings
  • Work individually throughout the semester: explore literature, write a report, peer-review, create and give two presentations
  • Full schedule link
  • Kickoff: Sep 13.

Registration

Explore the list of topics below and select at least 3 topics of your preference. Send a ranked list of your selected topics via email to ywang(at)uni-mannheim(dot)de until Sep 07. We will confirm your registration by Sep. 09. The actual topic assignment takes place soon after the registration deadline and we will notify you via e-mail. Our goal is, of course, to assign to you to one of your preferred topics.

Topics

The papers and articles listed below serve as an entry point to a topic; you are expected to explore related relevant literature on your own.

 

1. Translating Embeddings for Modeling Multi-relational Data,  NIPS 2013

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran

 

2. Holographic Embeddings of Knowledge Graphs, AAAI 2016

Maximilian Nickel, Lorenzo Rosasco and Tomaso Poggio

 

3. Complex Embeddings for Simple Link Prediction, ICML 2016

Theo Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, Guillaume Bouchard

 

4.On the Equivalence of Holographic and Complex Embeddings for Link Prediction, ACL 2017

Katsuhiko Hayashi, Masashi Shimbo

 

5. A Three-Way Model for Collective Learning on Multi-Relational Data, ICML 2011

Maximilian Nickel, Volker Tresp, Hans-Peter Kriegel

 

6. Discriminative Gaifman Models, NIPS 2015

Mathias Niepert

 

7. Knowledge-Based Trust: Estimating the Trustworthiness of Web Sources, VLDB 2015

Xin Luna Dong, Evgeniy Gabrilovich, Kevin Murphy, Van Dang

 

8. Random Walk Inference and Learning in A Large Scale Knowledge Base, EMNLP 2011

Ni Lao, Tom Mitchell, William W. Cohen

 

9. EMBEDDING ENTITIES AND RELATIONS FOR LEARNING AND INFERENCE IN KNOWLEDGE BASES, ICLR 2015

Bishan Yang, Wen-tau Yih, Xiaodong He , Jianfeng Gao & Li Deng

 

10. TransG : A Generative Model for Knowledge Graph Embedding, ACL 2016

Han Xiao, Minlie Huang, Xiaoyan Zhu

 

11. Typed Tensor Decomposition of Knowledge Bases for Relation Extraction, EMNLP 2014

Kai-Wei Chang, Wen-tau Yih,  Bishan Yang, Christopher Meek

 

12. Modeling Relation Paths for Representation Learning of Knowledge Bases, EMNLP 2015

Yankai Lin , Zhiyuan Liu , Huanbo Luan , Maosong Sun , Siwei Rao , Song Liu

 

13. Reasoning With Neural Tensor Networks for Knowledge Base Completion, NIPS 2013

Richard Socher , Danqi Chen, Christopher D. Manning, Andrew Y. Ng

 

Students are free to suggest alternative topics.

Resources

The following resources may be helpful:

  • Introduction to Statistical Relational Learning,  by Getoor and Taska
  • A Review of Relational Machine Learning for Knowledge Graphs, by Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich

 

Giving talks / writing reports:

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