Machine Learning Methods in Visualisation will be held as part of EuroVis 2019 in Porto, Portugal. The fourth edition of this co-located event will be part-tutorial and part-workshop so as to increase the interaction between researchers.
All activities take place on June 3 at the Eurovis 2019 venue, the Alfândega do Porto Conference Center. The joint opening and keynote take place in room Arrábida, all following activities take place in room S. João.
- 9:00 – 9:10 MLVis + EuroVA joint opening (room: Arrábida)
- 9:10 – 9:55 MLVis + EuroVA joint keynote (speaker: Samuel Kaski, room: Arrábida)
- 9:55 – 10:00 Transition to split workshops
- 10:00 – 10:40 MLVis Tutorial component (room: S. João)
- Dimensionality Reduction and Visual Interfaces (speaker: Jaakko Peltonen)
- Perception of Graph Sampling (speaker: Daniel Archambault)
- Evaluating Visualization (speaker: Ian Nabney)
- 10:40 – 11:10 Coffee break
Paper session (room: S. João):
- 11:10 – 11:30
On KDE-based brushing in scatterplots and how it compares to CNN-based brushing.
Chaoran Fan University of Bergen, Bergen, Norway
Helwig Hauser University of Bergen, Bergen, Norway
- 11:30 – 11:50
Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications.
Adrianna Janik Montreal Institute for Learning Algorithms, Montreal, Quebec, Canada
Kris Sankaran Montreal Institute for Learning Algorithms, Montreal, Quebec, Canada
Anthony Ortiz University of Texas at El Paso, El Paso, Texas, United States
- 11:50 – 12:10
Visual Analysis of Multivariate Urban Traffic Data Resorting to Local Principal Curves.
Pedro dOrey University of Porto, Porto, Porto, Portugal Instituto de Telecomunicações, Porto, Portugal
Carla Silva University of Porto, Porto, Portugal Instituto de Telecomunicações, Porto, Portugal
Ana Aguiar University of Porto, Porto, Portugal Instituto de Telecomunicações, Porto, Portugal
- 12:10 – 12:30
Visual Ensemble Analysis to Study the Influence of Hyper-parameters on Training Deep Neural Networks.
Sagad Hamid Westfälische Wilhelms-Universität, Münster, Germany
Adrian Derstroff Westfälische Wilhelms-Universität Münster, Münster, Germany
Soeren Klemm Mathematics and Computer Sciences, University of Muenster, Muenster, Germany
Quynh Quang Ngo Department of Mathematics and Computer Science/ Westfälische Wilhelms-Universität Münster, Institute of Computer Science, Münster, Germany
Xiaoyi Jiang Department of Computer Science, Münster, Germany
Lars Linsen Westfälische Wilhelms-Universität Münster, Münster, Germany
- 12:30 – 12:50 Panel and Closing (room: S. João).
Call for Papers
Part of the MLVis 2019 programme will consist of short papers.
We solicit short papers on machine learning methods in visualisation from both the machine learning and visualisation communities, addressing how the two technologies can be used together to provide greater insight to end users. Topics include but are not limited to: Explainable Machine Learning, Dimensionality Reduction, Visualisation of Clustering, Regression, and Classification, Steerable Machine Learning, Visualisation to Improve Machine Learning Models, Automation of Visualisation and Visual Analytics, Visualisation and Machine Learning in Text Analytics, Visualisation in Online Machine Learning
- Submission deadline: March 22, 2019 (extended deadline)
- Notification deadline: April 12, 2019
- Camera-ready deadline: April 24, 2019
- Workshop: June 3, 2019
All submission deadlines are at 23:59 GMT on the date indicated.
Paper submissions for MLVis should be at most 4 pages in the MLVis 2019 latex style, with an additional page allowed for references. All submissions must be original works that have not been published previously in any conference proceedings, magazine, journal, or edited book. Papers are to be submitted via the new PCS at: https://new.precisionconference.com/eurovis (choose society “VGTC” and conference/journal “MLVis 2019” when making your submission). The submissions do not need to be blind.
At least one author of an accepted paper must register and participate in the MLVis 2019 workshop to present the accepted work. Proceedings will be published by the Eurographics Association, and be stored on the Eurographics Digital Library.
In partnership with the EuroVA workshop, we intend to invite authors of selected MLVis 2019 papers to submit an extended version of their paper to a special issue of ACM Transactions on Interactive Intelligent Systems (TiiS) (https://tiis.acm.org/) with the title “Interactive Visual Analytics for Making Explainable and Accountable Decisions”.
Follow the MLVis website at https://uta.fi/mlvis for the latest details.
- Daniel Archambault (Swansea University, United Kingdom)
- Ian Nabney (University of Bristol, United Kingdom)
- Jaakko Peltonen (Tampere University, Finland)
International Program Committee
- Helwig Hauser (University of Bergen, Norway)
- John A. Lee (Universite catholique de Louvain, Belgium)
- David Lowe (Deep Learn)
- Torsten Möller (University of Vienna)
- Michel Verleysen (Universite catholique de Louvain, Belgium)
- Yong Wang (HKUST)
- Kanit Wongsuphasawat (Apple)