Fall 2018

Data Science Seminar

Lecturers: Mourad Khayati and Dingqi Yang 

Teaching language: English

Level: MSc students

Academic year: Fall 2018

Overview

Structure

Evaluation and Expectations

Schedule

List of Papers


Overview

The seminar on data science involves presentations that cover recent topics on data science. The area of this year’s seminar is graph embeddings. In the scope of this seminar, we investigate papers that describe algorithms and techniques to learn the representations of the vertices from a given network.


Structure

The goal for the students is to learn how to critically read and study research papers, how to describe  a paper in a report, and how to present it in a seminar. Under supervision, students will select one paper to study, contrast and compare with related work. This seminar aims to help students to gather in-depth knowledge of an advanced topic and develop the skills required to describe a complex problem from the word embedding area in the form of both a presentation, a written report and empirical  evaluation.

IMPORTANT NOTE: The papers will be distributed on a first come first serve basis.


Evaluation and Expectations

The final grade depends on the quality of the report, presentation, reproducibility experiments and active participation during the seminar. Each participant prepares a self contained report of min 6 pages and gives a presentation of 20 minutes. The report should describe in detail the proposed technique(s). The report might contain a small running example, counter example(s) and should explore the extreme cases where the proposed approach would perform best and worst. The reproducibility experiments consists of reproducing the same set of experiments introduced in the paper and making a 10 min demo about it.

Advices on how to:

IMPORTANT NOTE: Attendance is mandatory for the two class seminar sessions. The total number of participants will be limited to 10.


Schedule

Kickoff Meeting. Date: Tue, 25.09.2018, 14:00-17:00, room: A403
Setup and organization of seminar, and paper assignment

----------------------------------------------------------------------

Date: Tue, 1.11.2018
Report deadline
Batch1

Date: Tue, 6.11.2018, all day, room: B312 or C429
Office meeting with students from
Batch1

First Seminar Session. Date: Tue, 13.11.2018, 15:00-18:00, room: G514

Presentations of Batch1

----------------------------------------------------------------------

Date: Tue, 1.12.2018
Report deadline of
Batch2

Date: Tue, 4.12.2018, all day, room: B312 or C429
Office meeting with students from
Batch2

Second Seminar Session. Date: Tue, 11.12.2018, 14:15-17.00, room: G314

Presentations of Batch2

----------------------------------------------------------------------

Date: Tue, 15.01.2019
Deadline final Report of
Batch1 and Batch2


Paper Assignment

The papers will be distributed on a first come first serve basis. Please use the following link to select one paper among the list of papers.

Paper & code

Presentation Date

Presenter

Supervisor

First Report Deadline

(1) DeepWalk: Online Learning of Social Representations, KDD 2014. code: link

13.11.2018

Stefan Jonas

Dingqi Yang

01.11.2018

(2) node2vec: Scalable Feature Learning for Networks, KDD 2016. code: link

11.12.2018

Julia Eigenmann

Dingqi Yang

01.12.2018

(4) Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec, WSDM 2018. code: link

11.12.2018

Fabio Degiacomi

Dingqi Yang

01.12.2018

(5) LINE: Large-scale information network embedding, WWW 2015.

code: link

13.11.2018

Melike Geçer

Dingqi Yang

01.11.2018

(9) GraRep: Learning Graph Representations withGlobal Structural Information.  CIKM 2015. code: link

11.12.2018

Biswas Mili

Mourad Khayati

01.12.2018

(11) Co-Evolution Model for Social Network Evolving and Opinion Migration, KDD 2017. code: link

13.11.2018

Tofunmi Ajayi

Mourad Khayati

01.11.2018