Major breakthroughs in Artificial Intelligence (AI) have raised strong interests from research and industry towards Machine Learning (ML), the discipline of AI that aims at building software that automatically learns from data. As a result, ML systems increasingly gain popularity and will soon proliferate in a broad range of domains. However, they also raise many questions, in particular regarding their reliable engineering. Conversely, recent advances in Software Engineering (SE) themselves rely on ML. Several software development activities can thus now benefit from AI-based assistance and we expect many more in the coming years.
This workshop aims at bringing together the SE and ML communities to reflect on the potential symbioses between their respective disciplines. As such, it targets innovative ML applications improve SE practices, as well as new engineering methods for ML-based systems.
Major breakthroughs in Artificial Intelligence (AI) have raised strong interests from research and industry towards Machine Learning (ML), the discipline of AI that aims at building software that automatically learns from data. As a result, ML systems increasingly gain popularity and will soon proliferate in a broad range of domains. However, they also raise many questions, in particular regarding their reliable engineering. Conversely, recent advances in Software Engineering (SE) themselves rely on ML. Several software development activities can thus now benefit from AI-based assistance and we expect many more in the coming years.
This workshop aims at bringing together the SE and ML communities to reflect on the potential symbioses between their respective disciplines. As such, it targets innovative ML applications improve SE practices, as well as new engineering methods for ML-based systems.
Topics include, but are not limited to:
We invite original papers from 2 to 10 pages in the conference format
(two columns
IEEE conference publication format
, title in 24pt font and full text in 10pt font, LaTeX users must use
(
ACM Proceedings Template
, LaTEX users must use \documentclass[10pt,conference]{IEEEtran}
without including the compsoc
or compsocconf
option)
\documentclass[sigconf]{acmart}
)
describing positions and visions as well as technical contributions and experience reports. Reports on existing research projects
(e.g., H2020) and industrial perspectives are also welcome.
The proceedings will be published by IEEE through the IEEE Xplore platform.
The review process is single-blind. Each contribution will be reviewed by at least three members of the programme committee.
08:00. |
Registration. |
09:00. |
Opening. |
09:05. |
Keynote: Scikit-learn: Engineering High-Quality Machine-Learning Software with a Community. |
10:00. |
Coffee. |
Session 1. |
|
10:30. |
Applying Graph Kernels to Model-Driven Engineering Problems. |
11:00. |
Learning-Based Testing for Autonomous Systems using Spatial and Temporal Requirements. |
11:30. |
Automatically Assessing Vulnerabilities Discovered by Compositional Analysis. |
12:00. |
Lunch. |
Session 2. |
|
13:30. |
A Deep Learning Approach to Program Similarity. |
14:00. |
A Language-Agnostic Model for Semantic Source Code Labeling. |
14:30. |
Fast Deployment and Scoring of Support Vector Machine Models in CPU and GPU. |
15:00. |
Coffee. |
Invited Software Mining Workshop session. |
|
15:30. |
See the Software Mining workshop program for details. |
18:00. |
Closing. |