Write a Blog >>
ESEC/FSE 2021
Thu 19 - Sat 28 August 2021 Clowdr Platform
Wed 25 Aug 2021 19:10 - 19:20 - SE & AI—Search Based Software Engineering Chair(s): Myra Cohen
Thu 26 Aug 2021 07:10 - 07:20 - SE & AI—Search Based Software Engineering Chair(s): Phuong T. Nguyen

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.

Wed 25 Aug

Displayed time zone: Athens change

19:00 - 20:00
SE & AI—Search Based Software EngineeringResearch Papers +12h
Chair(s): Myra Cohen Iowa State University
19:00
10m
Paper
Bias in Machine Learning Software: Why? How? What to Do?Distinguished Paper Award
Research Papers
Joymallya Chakraborty North Carolina State University, Suvodeep Majumder North Carolina State University, Tim Menzies North Carolina State University
DOI Pre-print
19:10
10m
Paper
Understanding Neural Code Intelligence through Program SimplificationArtifacts Available
Research Papers
Md Rafiqul Islam Rabin University of Houston, Vincent J. Hellendoorn Carnegie Mellon University, Amin Alipour University of Houston
DOI Pre-print Media Attached
19:20
10m
Paper
Multi-objectivizing Software Configuration TuningArtifacts Available
Research Papers
Tao Chen Loughborough University, Miqing Li University of Birmingham
DOI Pre-print
19:30
30m
Live Q&A
Q&A (SE & AI—Search Based Software Engineering)
Research Papers

Thu 26 Aug

Displayed time zone: Athens change

07:00 - 08:00
SE & AI—Search Based Software EngineeringResearch Papers
Chair(s): Phuong T. Nguyen University of L’Aquila
07:00
10m
Paper
Bias in Machine Learning Software: Why? How? What to Do?Distinguished Paper Award
Research Papers
Joymallya Chakraborty North Carolina State University, Suvodeep Majumder North Carolina State University, Tim Menzies North Carolina State University
DOI Pre-print
07:10
10m
Paper
Understanding Neural Code Intelligence through Program SimplificationArtifacts Available
Research Papers
Md Rafiqul Islam Rabin University of Houston, Vincent J. Hellendoorn Carnegie Mellon University, Amin Alipour University of Houston
DOI Pre-print Media Attached
07:20
10m
Paper
Multi-objectivizing Software Configuration TuningArtifacts Available
Research Papers
Tao Chen Loughborough University, Miqing Li University of Birmingham
DOI Pre-print
07:30
30m
Live Q&A
Q&A (SE & AI—Search Based Software Engineering)
Research Papers