Fall 2019
Data Science Seminar
Lecturers: Mourad Khayati and Dingqi Yang
Teaching language: English
Level: MSc students
Academic year: Fall 2019
Overview
The seminar on data science involves presentations that cover recent topics on data science. The area of this year’s seminar is neural networks. In the scope of this seminar, we investigate papers that describe algorithms and techniques that use different variants of neural networks to perform data analytics in particular for fashion data.
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, and to 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 neural network area in the form of both a presentation, a written report and an 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 30 minutes. The report should describe in detail the proposed technique(s). The report might contain a small running example, counter example(s) if any, and should explore the extreme cases where the proposed approach would perform best and worst. The reproducibility experiments consist of reproducing the same set of experiments introduced in the paper.
Advice 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, 24.09.2019, 14:15-15:30, room: C421
Setup and organization of seminar, and paper assignment
----------------------------------------------------------------------
Date: Tue, 05.11.2019
Report deadline Batch1
Date: Tue, 12.11.2019, all day, room: C433 or C429
Office meeting with students from Batch1
First Seminar Session. Date: Tue, 19.11.2019, 14:15-17:15, room: G514 (change to D130 at 16:00)
Presentations of Batch1
----------------------------------------------------------------------
Date: Tue, 19.11.2019
Report deadline of Batch2
Date: Tue, 26.11.2019, all day, room: C433 or C429
Office meeting with students from Batch2
Second Seminar Session. Date: Tue, 03.12.2019, 14:15-17.15, room: 001 (PER17)
Presentations of Batch2
----------------------------------------------------------------------
Date: Tue, 14.01.2020
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 |
MTNet: A Neural Approach for Cross-Domain Recommendation with Unstructured Text. KDD 2018. Code: http://www.cs.cmu.edu/~ajit/cmf/ | 19.11.2019 | Stefan Jonas | M. Khayati | 05.11.2019 |
node2vec: Scalable Feature Learning for Networks, KDD 2016. | 19.11.2019 | Julia Eigenmann | D. Yang | 05.11.2019 |
BRITS: Bidirectional Recurrent Imputation for Time Series. NIPS 2018. Code: https://github.com/NIPS-BRITS/BRITS | 19.11.2019 | Louis Müller | M. Khayati | 05.11.2019 |
Convolutional 2D Knowledge Graph Embeddings, AAAI 2018. Code: https://github.com/TimDettmers/ConvE | 03.12.2019 | Gabriela-Carmen Dinica | D. Yang | 19.11.2019 |
Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts. AAAI 2016. Code: https://github.com/yongqyu/STRNN | 03.12.2019 | Benjamin Fankhauser | D. Yang | 19.11.2019 |
Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks. WWW 2019. Code: https://github.com/CRIPAC-DIG/NGNN | 03.12.2019 | Maurice Rupp | M. Khayati | 19.11.2019 |
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network. NAACL 2018. Code: https://github.com/daiquocnguyen/ConvKB | 19.11.2019 | Shaokang YANG | D. Yang | 05.11.2019 |
Visually-Aware Fashion Recommendation and Design with Generative Image Models. ICDM 2017. Code: https://github.com/kang205/DVBPR | 03.12.2019 | Jiyoung Lee | M. Khayati | 19.11.2019 |
Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering. WWW 2016. Code: https://sites.google.com/view/ruining-he/ | M. Khayati | |||
What to Do Next: Modeling User Behaviors by Time-LSTM. IJCAI 2017. Code: https://github.com/DarryO/time_lstm | D. Yang | |||
Semi-Supervised Classification with Graph Convolutional Networks. ICLR 2017. Code: https://github.com/tkipf/gcn | D. Yang |