The Special Session on

        Representation Learning meets Meta-heuristic Optimization (RepL4Opt)
        http://cs.ijs.si/repl4opt/

at the 2021 IEEE Congress on Evolutionary Computation (CEC 2021) in Kraków, Poland, June 28 – July 1, 2021 welcomes submissions of original research articles on all aspects of Representation Learning relevant to optimization with evolutionary algorithms and related approaches.

Accepted papers will be part of the IEEE CEC Proceedings.
Submission deadline (extended): February 21, 2021
Important: Make sure to select the RepL4Opt special session (SS-57) when submitting!

SCOPE

Per-instance automated algorithm selection and configuration techniques
 use high-level information about the problem instance to train
meta-models that aim to predict which algorithm or  which configuration
works well on this particular instance.  Per-instance selection and
configuration have shown promising  performances for a number of
classical optimization problems, including  SAT solving, AI planning,
etc. In the context of black-box  optimization, properties of the
instance need to be inferred from samples.  Key design questions in
this context concern  the selection of meaningful features to quantify
the instance,  the efficient computation of these features, the  number
of samples required to obtain reliable approximations, the 
distribution of these samples, the possibility to use algorithms’ 
trajectory data for feature computation, and many more. Research 
addressing these questions is subsumed under the term “exploratory 
landscape analysis” (ELA). In ELA, a large number of different features
 have been proposed, which raise up the need of feature selection,
since  many features can be highly correlated and have a decremental
impact on  understanding of the underlying recommendations. This is
where  representation learning comes into play. Representation learning
has  its most important applications in machine learning, where bias
and  redundancies in data can have severe effects on performance. It
focuses  on methods that automatically learn new data representations
(i.e.,  feature engineering) using the raw data needed to improve the 
performance of machine learning tasks. Representation learning methods 
are also successfully used to reduce the dimension of the data, via 
automatically detecting correlations.

In this special session, we are particularly interested in studying how
representation learning can contribute to improve performance and to a
better understanding of ELA-based analyses, e.g., by automatically
reducing bias, correlations and redundancies in the feature data.

TOPICS OF INTEREST

We welcome submissions on the following topics:
– Representation learning techniques for structured, unstructured, and
graph data
– Exploratory landscape analysis (ELA) for feature engineering of the
landscape space
– Feature selection, ranking and sensitivity analysis
– Sensitivity analysis of sampling techniques applied in ELA
– Representation learning applied on landscape data
– Representation learning applied on performance data
– Improving understanding of data (landscape and/or performance)
through visualization techniques
– Landscape data representation in automatic algorithm selection and
configuration
– Performance data representation in automatic algorithm selection and
configuration
– Machine learning for automatic algorithm selection and configuration
– Meta-learning
– Transfer of approaches between machine learning and optimization
– Taxonomies/ontologies for describing the algorithm instance space
– Complementary analysis of different benchmarking datasets
– Any other topic relating representation learning to sampling-based
optimization

SUBMISSION GUIDELINES

All submissions should follow the CEC2021 submission guidelines
provided at IEEE CEC 2021 Submission Website
(https://cec2021.mini.pw.edu.pl/en/calls/call-for-papers). Special
session papers are treated the same as regular conference papers.
Please specify that your paper is for the Special Session on RepL4Opt:
Representation Learning meets Meta-heuristic Optimization (SS-57). All
papers accepted and presented at CEC 2021 will be included in the
conference proceedings published by IEEE Explore.

In order to participate to this special session, full or student
registration of CEC 2021 is needed.

IMPORTANT DATES

– Paper submission: 21 February 2021
– Paper acceptance notification: 6 April 2021
– Final paper submission: 23 April 2021
– Conference: 28 June – 1 July 2021

ORGANIZERS

Tome Eftimov
Computer Systems Department
Jožef Stefan Institute
Slovenia

Carola Doerr
LIP6
Sorbonne University, CNRS
France

Peter Korošec
Computer Systems Department
Jožef Stefan Institute
Slovenia