Write a Blog >>
ESEC/FSE 2021
Mon 23 - Sat 28 August 2021 Athens, Greece

This program is tentative and subject to change.

Wed 25 Aug 2021 19:00 - 19:20 - AI—Search Based Software Engineering
Thu 26 Aug 2021 07:00 - 07:20 - AI—Search Based Software Engineering

A wide range of code intelligence (CI) tools, powered by deep neural networks, have been developed recently to improve programming productivity and perform program analysis. To reliably use such tools, developers often need to reason about the behavior of the underlying models and the factors that affect them. This is especially challenging for tools backed by deep neural networks. Various methods have tried to reduce this opacity in the vein of “transparent/interpretable-AI”. However, these approaches are often specific to a particular set of network architectures, even requiring access to the network’s parameters. This makes them difficult to use for the average programmer, which hinders the reliable adoption of neural CI systems. In this paper, we propose a simple, model-agnostic approach to identify critical input features for models in CI systems, by drawing on software debugging research, specifically delta debugging. Our approach, SIVAND, uses simplification techniques that reduce the size of input programs of a CI model while preserving the predictions of the model. We show that this approach yields remarkably small outputs and is broadly applicable across many model architectures and problem domains. We find that the models in our experiments often rely heavily on just a few syntactic features in input programs. We believe that SIVAND’s extracted features may help understand neural CI systems’ predictions and learned behavior.

This program is tentative and subject to change.

Conference Day
Wed 25 Aug

Displayed time zone: Athens change

19:00 - 20:00
AI—Search Based Software EngineeringResearch Papers +12h
19:00
20m
Research paper
Understanding Neural Code Intelligence Through Program Simplification
Research Papers
Md Rafiqul Islam RabinUniversity of Houston, Vincent J. HellendoornCMU, Amin AlipourUniversity of Houston
DOI Pre-print Media Attached
19:20
20m
Talk
Multi-Objectivizing Software Configuration Tuning
Research Papers
Tao ChenLoughborough University, Miqing LiUniversity of Birmingham, UK
Pre-print
19:40
20m
Talk
Bias in Machine Learning Software: Why? How? What to do?Distinguished Paper Award
Research Papers
Joymallya ChakrabortyNorth Carolina State University, USA, Suvodeep MajumderNorth Carolina State University, Tim MenziesNorth Carolina State University, USA
Pre-print

Conference Day
Thu 26 Aug

Displayed time zone: Athens change

07:00 - 08:00
AI—Search Based Software EngineeringResearch Papers
07:00
20m
Research paper
Understanding Neural Code Intelligence Through Program Simplification
Research Papers
Md Rafiqul Islam RabinUniversity of Houston, Vincent J. HellendoornCMU, Amin AlipourUniversity of Houston
DOI Pre-print Media Attached
07:20
20m
Talk
Multi-Objectivizing Software Configuration Tuning
Research Papers
Tao ChenLoughborough University, Miqing LiUniversity of Birmingham, UK
Pre-print
07:40
20m
Talk
Bias in Machine Learning Software: Why? How? What to do?Distinguished Paper Award
Research Papers
Joymallya ChakrabortyNorth Carolina State University, USA, Suvodeep MajumderNorth Carolina State University, Tim MenziesNorth Carolina State University, USA
Pre-print