Connectionists: Call for Papers: Embeddings and Representation Learning for Structured Data (ESANN 2019 Special Session)

[Benjamin Paassen]

Dear Connectionists subscribers,

this is a reminder regarding our call for papers for contributions on
'Embeddings and Representation Learning for Structured Data', such as
sequences, trees, and graphs. We will host a special session on this
topic at next year's European Symposium on Artificial Neural Networks,
Computational Intelligence and Machine Learning (ESANN 2019; 24 - 26
April 2019 in Bruges, Belgium). We cordially invite you to
submit your work to this special session. The submission deadline is at
*November 19th, 2018*.

# DESCRIPTION

Learning models of structured data, such as sequences, trees, and
graphs, has become a rich and promising research objective in many
fields of machine learning, such as (deep) neural networks,
probabilistic models, kernels, metric learning, and dimensionality
reduction. All these seemingly disparate approaches are connected by
their construction of vectorial representations and embeddings of
structured data, be it implicit or explicit, fixed or learned,
deterministic or stochastic. Such embeddings can not only be utilized
for classification or regression, but for generation of structured data,
visualization, and interpretation.

# TOPICS OF INTEREST

This session calls for contributions which provide novel methods to
construct embeddings of structured data, new methods to utilize existing
embeddings, and theoretic research regarding the properties of such
embeddings. More specifically, topics of interest include, but are not
limited to, the following:

* Recurrent and recursive neural networks for structured data
* Neural networks for graphs
* Auto-Encoding models for structured data
* Generative adversarial networks for structured data
* Representation Learning for structured data
* Deep models of structured data
* Sequence, tree, and graph kernels with explicit vectorial representations
* Kernel methods for structured data
* Markov models for representation of sequences, trees, or graphs
* Theoretical considerations on learning theory and dimensionality of
embeddings of structured data
* Metric learning for structured data
* Dimensionality reduction techniques for structured data
* Interpretability of vectorial representations of structured data

# SUBMISSION

Submissions must be made on the ESANN website via the following link:

https://www.elen.ucl.ac.be/esann/index.php?pg=submission

Each paper submission will be peer-reviewed and authors will receive a
notification of acceptance at *January 31st, 2019* as either an oral or
poster presentation. All papers are six pages and will be published in
the ESANN proceedings (
https://www.elen.ucl.ac.be/esann/proceedings/electronicproceedings.htm ).

# IMPORTANT DATES

Submission of papers: 		19 November 2018
Notification of acceptance: 	31 January 2019
ESANN conference: 		24 - 26 April 2019

# SPECIAL SESSION ORGANIZERS

* Benjamin Paaßen, Bielefeld University, Germany
* Claudio Gallicchio, University of Pisa, Italy
* Alessio Micheli, University of Pisa, Italy
* Alessandro Sperduti, University of Pisa, Italy