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.


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