|
Call for Papers and Datasets
Data and Machine Learning Approaches with Multiple Views
Workshop In conjunction with ECML-PKDD’19
https://damvl.lis-lab.fr/
Recent years have witnessed new frameworks/algorithms able to deal with multiple views, such as Multiple Kernel Learning, Boosting, Co-regularized, Deep approaches. Such algorithms come from the Machine Learning community and find applications in many different areas, such as Multimedia Indexing, Computer Vision, Bio-informatics, Neuro-imaging… Multiview learning, naturally enough, emphasises the potential benefits of learning through collaboration with multiple sources of data (e.g. video document can be described through images, sound, motion, text).
Depending on the context, this issue of learning from multiple descriptions of data goes under the name of multiview learning (machine learning, computer vision), multimodality fusion (multimedia), among others. This workshop is the opportunity to bring together theoretical and applicative communities around multiview learning, which could lead to significant contributions and exchanges between Machine Learning and natural fields of applications such as biology, computer vision, marketing, ecology, health, computer vision, etc.
The workshop aims at bringing together people interested with multi-view learning, both from dataset providers to researchers in machine learning. Such a way, researchers could easily have the opportunity to inspect the reality of some true learning problems related to multi-view learning, meanwhile providers of natural multi-viewed data could get aware of the many current or potential solutions to address their learning tasks.
This workshop will dedicate the morning to talks about multi-view theory and algorithms and talks about multi-view real datasets/tasks. In the afternoon, a hackathon on one of the selected datasets will be organized where attendants are expected to produce a team work including datasets providers for drawing relevant solutions. The call for contributions is then twofolds:
Call for papers (extended abstracts) on multi-view learning methods, theory, and applications
Call for true multiview datasets (for presentation of the dataset and maybe for the hackhaton)
Topics of interests
The main objectives of this workshop are to 1) introduce recent development in machine learning with multiview setting, 2) focus on various problematics in any field where such a setting arises and 3) offer new directions and discuss about open questions that appear.
In particular, the following topics specific to multi-view learning are relevant:
• Diversity / Complementarity / (Dis-)agreement between views
• Missing data or views / Noisy data or views / Noisy annotations
• Multiview for Large-scale / Big data
• Multiview for small data
• Relevant losses and theory for multiview learning
• Scaling multiview approaches
• Multiview and Ranking / Learn with imbalanced data set
• Variables and views selection
• Representation Learning (deep or not) with multiple views
• Multiview for domain adaptation / transfer learning / optimal transport
Please note that at least one author of each accepted paper should register for the ECML/PKDD conference.
Important dates
Abstract registration deadline June 7, 2019
Dataset and paper submission deadline June 14, 2019
Workshop paper/dataset acceptance notification July 19, 2019
Accepted datasets and papers releases and camera-ready deadline July 26, 2019
Submission Guidelines
https://easychair.org/my/conference?conf=workshopdamvl1
The workshop will be based on invited talks, contributed talks, datasets presentations, posters and demos. In that respect, we have three submission types:
• unpublished (original) works (max 8 pages excluding references, LNCS format).
• recently published works (extended abstract, max 4 pages including references, LNCS format). The extended abstract has to mention where and when the paper has been published.
• a dataset description together with proposed machine learning task(s) on it (extended abstract, max 4 pages, LNCS format). The authors must explicitly specify it they wish to submit their
dataset for the hackathon (such a submission requires that the dataset must be available to the program cmomittee upon request).
Papers and datasets will be evaluated according to their originality and relevance to the workshop, and should include author names, affiliations, contact information, and an abstract. Accepted papers have to be presented orally or as a poster, and will be available on the website. Accepted dataset/task for the hackathon will be publicly available, and will benefits from the solutions provided by the attendants at the workshop.
Proceedings will be edited as a digital report, and published either through a scientific publisher in collaboration with LNCS, or on arXiv.
Committees
Program Committee
Sahely Bhadra, Indian Institute of Technology, Palakkad, Kerala, India
Cécile Capponi, Aix-Marseille University, France (co-chair)
Ludovic Denoyer, Facebook FAIR, Paris, France
Isabelle Guyon, Orsay University, Saclay, France
Amaury Habrard, Jean-Monnet University, Saint-Etienne, France
Riikka Huusari, Aix-Marseille University, France
Hachem Kadri, Aix-Marseille University, France
Stéphane Marchand-Maillet, University of Geneva, Switzerland
Juho Rousu, University of Aalto, Finland (co-chair)
Shiliang Sun, East China Normal University, Shangai, China
Sylvain Takerkart, Aix-Marseille University, France
Paul Villoutreix, Turing Center (Centuri), Marseille, France
Organizing committee
Stéphane Ayache, Aix-Marseille University, France
Cécile Capponi, Aix-Marseille University, France
Rémi Emonet, Jean-Monnet University, Saint-Etienne, France
Isabelle Guyon, Orsay University, Paris, France.
Contact
All questions about submissions should be emailed to cecile.capponi +at+ lis-lab +dot+ fr and/or juho.rousu +at+ aalto +dot+ fi
|
