The workshop on Logic-based Methods in Machine Learning (LMML 2022) is a satellite workshop of the Federated Logic Conference (FLoC 2022) and will take place on July 31, 2022, in Haifa, Israel.

CALL FOR SPOTLIGHT TALKS

The workshop program will consist of invited talks and contributed spotlight talks of 10 minutes.

If you are interested in giving a spotlight talk, please submit an extended abstract (3 pages) on Easychair by June 7, 2022 (AoE) under the following link:

https://easychair.org/conferences/?conf=lmml2022

Speakers will be notified by June 15 about acceptance. Since the workshop will not publish any archival proceedings, the submission of extended abstracts of papers that have been published or submitted elsewhere is welcome. Speakers with accepted contributions are expected to register for the workshop and to give the spotlight talk at the workshop.

TOPICS AND AIMS

The far-reaching success of Machine Learning (ML) motivates an ever-growing range of applications. However, the most successful ML models are opaque (“black-box”) because they do not support the explainability or verifiability of their predictions. Recent years have witnessed the emergence of several successful and promising approaches to overcome these limitations with the help of logic-based techniques, including the well-developed technologies of SAT/CP-assisted reasoning and optimization, including the well-developed technologies of SAT-, MaxSAT-, SMT-, and MIPS-solving, constraint optimization, and Model Counting.

This workshop aims at bringing together researchers from various fields that work on SAT-based methods for (i) learning interpretable ML models, (ii) computing explanations for black-box ML models, and (iii) verification of black-box ML models.

ORGANIZERS

Alexey Ignatiev, Monash University, Melbourne, Australia Stefan Szeider, TU Wien, Vienna, Austria

FURTHER INFORMATION

https://ac.tuwien.ac.at/LMML2022/
https://www.floc2022.org