Attend and Represent: A Novel View on Algorithm Selection for Software Verification
Today, a plethora of different software verification tools exist. When having a concrete verification task at hand, software developers thus face the problem of algorithm selection. Existing algorithm selectors for software verification typically use handpicked program features together with (1) either manually designed selection heuristics or (2) machine learned strategies. While the first approach suffers from not being transferable to other selection problems, the second approach lacks interpretability, i.e., insights into reasons for choosing particular tools.
In this paper, we propose a novel approach to algorithm selection for software verification. Our approach employs representation learning together with an attention mechanism. Representation learning circumvents feature engineering, i.e., avoids the handpicking of program features. Attention permits a form of interpretability of the learned selectors. We have implemented our approach and have experimentally evaluated and compared it with existing approaches. The evaluation shows that representation learning does not only outperform manual feature engineering, but also enables transferability of the learning model to other selection tasks.
Thu 24 SepDisplayed time zone: (UTC) Coordinated Universal Time change
08:00 - 09:00 | Verification and TestingTool Demonstrations / Industry Showcase / Research Papers at Koala Chair(s): Jun Sun Singapore Management University | ||
08:00 20mTalk | Attend and Represent: A Novel View on Algorithm Selection for Software Verification Research Papers | ||
08:20 20mTalk | Lightweight MBT Testing for National e-Health Portal in Norway Industry Showcase Davrondzhon Gafurov Norsk Helsenett SF, Margrete Sunde Grovan Norsk Helsenett SF, Margrete Sunde Grovan Norsk Helsenett SF | ||
08:40 10mTalk | Speeding up GUI Testing by On-Device Test Generation Tool Demonstrations Nataniel Borges Jr. CISPA Helmholtz Center for Information Security, Jenny Rau CISPA Helmholtz Center for Information Security, Andreas Zeller CISPA, Germany | ||
08:50 10mTalk | PerfCI: A Toolchain for Automated Performance Testing during Continuous Integration of Python Projects Tool Demonstrations Omar Javed Università della Svizzera italiana, Joshua Heneage Dawes University of Manchester and CERN, Marta Han University of Zagreb and CERN, Giovanni Franzoni CERN, Andreas Pfeiffer CERN, Giles Reger University of Manchester, Walter Binder University of Lugano, Switzerland |