PhD Forum

DESCRIPTION

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) includes a PhD student Forum on machine learning and data mining on the monday, 16.9.2019.

The purpose of this forum is to provide an environment specifically for junior PhD students to exchange ideas and experiences with peers in an interactive atmosphere and to get constructive feedback from senior researchers in machine learning, data mining, and related areas.

The focus of the discussion at the PhD Forum would be the work in progress of junior PhD students, with 1-3 years of research experience towards their dissertation.

During the forum, researchers with experience in supervising and examining doctoral students will participate and provide constructive feedback and advice to the participants.

It is an excellent opportunity for developing person-to-person networks to the benefit of the PhD students in their future careers.

INITIAL PROGRAM

  • 09:00 – 10h30 The ins and outs of reviewing: the good, the bad, and the ugly tutorial: first round

  • 10:30 – 11:00 Coffee Break

  • 11:00 – 12:40 The ins and outs of reviewing: the good, the bad, and the ugly tutorial: second round

  • 12:40 – 14:00 PhD Forum Lunch (to be confirmed)

  • 14:00 – 14:05  Welcome

  • 14:05 – 14:30 Session 1: mostly deep learning – Chair: Ulf Brefeld
    • Elena Battaglia and Ruggero Pensa: Parameter-less Tensor Co-clustering
    • Gesina Schwalbe and Ute Schmid: Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks
    • Gabriel Campero Durand: Production-ready self-driving data management with Deep Reinforcement Learning
    • Muhammad Ali and Ashiq Anjum: Accelerating Deep Learning Feed Forward Networks using Edge Enhanced Approach
    • Marie Ossenkopf: Emerging Complex Communication Patterns

  • 14:30 – 14:35 short break (stretch legs, shake hands)

  • 14:35 – 14:55 Session 2: mostly interpretability – Chair: Luis Galarraga
    • Anna Nguyen: Explainable Neural Architecture Search
    • Yue Zhang, Tony Kaoma, Arnaud Muller, Xuewei Wang, Gunnar Dittmar, Simone P. Niclou, Jean-Pierre Kocher and Francisco Azuaje: Interpreting Random Forests With Ensemble Networks for Omics Data Analysis
    • Yichang Wang, Rémi Emonet, Elisa Fromont, Simon Malinowski, Etienne Menager, Loïc Mosser and Romain Tavenard: Learning Interpretable Times Series Shapelets through Adversarial Regularization
    • Andrea Tonon and Fabio Vandin: Finding the True Frequent Sequential Patterns

  • 14:55 – 15:00 buffer because we will surely go overtime

  • 15:00 – 15:20 official coffee break

  • 15:20 – 15:45 Session 3: monstly data mining – Chair: Wouter Duivesteijn
    • Chang Sun: Privacy-Preserving Data Mining Models in Vertically Partitioned Data
    • Samudra Herath, Matthew Roughan and Gary Glonek: Name-like Numbers for Simulating Names in Entity Resolution
    • Gregory Martin, Laurence Rozé, Alexandre Termier, Élisa Fromont and Matthieu Donain: Free-Floating Car-Sharing Service Optimization
    • Cedric Kulbach: AutoPipeline - Building meaningful pipeline orchestrations
    • Sven Voigt and Xiaoming Fu: Measuring City Attractiveness Using Commuting Data
  • 15:45 – 16:15 Poster session
    • Denis Steckelmacher, Hélène Plisnier, Diederik M. Roijers and Ann Nowé: Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
    • Wenjie Feng, Shenghua Liu and Xueqi Cheng: CatchCore: Catching Hierarchical Dense Subtensor
    • Huiping Chen, Giulia Bernardini, Alessio Conte, Roberto Grossi, Grigorios Loukides, Nadia Pisanti, Solon P. Pissis and Giovanna Rosone: String Sanitization: A Combinatorial Approach
    • Jack Lanchantin, Arshdeep Sekhon and Yanjun Qi: Neural Message Passing for Multi-Label Classification
    • Ghadeer Abuoda, Gianmarco De Francisci Morales and Ashraf Aboulnaga: Link Prediction via Higher-Order Motif Features
    • S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya and Hideki Asai: A Stochastic Quasi-Newton Method with Nesterov’s Accelerated Gradient
    • Aleksandra Burashnikova, Yury Maximov and Massih-Reza Amini: Sequential Learning over Implicit Feedback for Robust Large-Scale Recommender Systems
    • Jann Goschenhofer, Franz Pfister, Kamer Yuksel, Bernd Bischl, Urban Fietzek and Janek Thomas: Wearable-based Parkinson’s Disease Severity Monitoring using Deep Learning
    • Florian Seiffarth, Tamás Horváth and Stefan Wrobel: Maximal Closed Set and Half-Space Separations in Finite Closure Systems
    • Hadar Sivan, Moshe Gabel and Assaf Schuster: Online Linear Models for Edge Computing
    • Zac Wellmer and James Kwok: Policy Prediction Network
    • Paulo Roberto de Oliveira da Costa, Jason Rhuggenaath, Yingqian Zhang, Alp Akcay, Wan-Jui Lee and Uzay Kaymak: Data driven policy on feasibility determination for train shunting problem
    • Marco Roberti, Giovanni Bonetta, Rossella Cancelliere and Patrick Gallinari: Copy Mechanism and Tailored Training for Character-based Data-to-text Generation
  • 16:15 – 16:20 Closing and go to opening session

SUBMISSION INFORMATION

The ECMLPKDD PhD Forum spans various topics of data mining, machine learning, and work in related fields such as databases, artificial intelligence, statistics, information retrieval, multimedia and the Web. Topics in specific domains such as bioinformatics and the more general science informatics are also encouraged. Participants with interdisciplinary work across the areas are particularly welcome.

The PhD Forum is open for two types of submissions:

  • Accepted papers at ECMLPKDD (Research or ADS tracks): the authors of the research or ADS accepted papers (with a PhD student as main author) have the opportunity to summarize their work in the PhD forum.
  • Work-in-progress papers: we welcome submissions from PhD students at early and middle stages of their PhD work. As guideline, we recommend that the submission is structured to explain 1) what the problem is, 2) why it is important, 3) why existing solutions in literature are insufficient, 4) how your approach works, and 5) optionally some preliminary experiments (4 pages, max 6 pages).

The purpose is to obtain feedback regarding future plans, and technical feedback on topic and writing.

Note that:

  • For work in progress papers, the only criterion for acceptance is that the submission is clearly structured and written in English language, and that it is of sufficient maturity to enable the audience of the PhD forum to provide constructive feedback.
  • Papers will not be formally published. However, unless the authors opt-out, they will be made publicly available through the conference website.
  • All accepted papers will be presented in short format (5 minutes) + questions.
  • The first author must be a PhD student who is less than 4 years into his PhD. Co-authors may include the research advisors, committee members, and other collaborators as needed.
  • The PhD student must register for the conference and be present at the PhD Forum.
  • We will ask each PhD student to participate in the review process by reviewing one paper.

SUBMISSION INSTRUCTIONS

The papers must be written in English and formatted according to the Springer LNAI guidelines. For accepted ECMLPKDD papers, you send the PDF as submitted.

Author instructions and style files can be downloaded at: http://www.springer.de/comp/lncs/authors.html.

Papers should be submitted in PDF format using the online easychair submission system.

DEADLINES

Paper Submission Deadline:   14. June 2019 24. June 2019
Author Notification:   19. July 2019

CONTACT

In case you have any question, please do not hesitate to contact the PhD Forum Chairs (Tias Guns and Tassadit Bouadi) at phd_chairs[at]ecmlpkdd2019.org