- author = "Jose Pablo {Cambronero Sanchez}",
- title = "Mining Software Artifacts for use in Automated Machine Learning",
- school = "Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology",
- year = "2021",
- address = "USA",
- month = may # " 13, 2021",
- keywords = "genetic algorithms, genetic programming, SBSE, TPOT",
-
URL = "
https://dspace.mit.edu/handle/1721.1/139465",
-
URL = "https://hdl.handle.net/1721.1/139465",
-
URL = "https://www.csail.mit.edu/event/mining-software-artifacts-use-automated-machine-learning",
-
URL = "
https://www.josecambronero.com/pdf/JCambronero-PhD-EECS-June2021.pdf",
-
URL = "https://dspace.mit.edu/bitstream/handle/1721.1/139465/Cambronero-jcamsan-PhD-EECS-2021-thesis.pdf?sequence=1&isAllowed=y",
- size = "149 pages",
-
abstract = "Successfully implementing classical supervised machine
learning pipelines requires that users have software
engineering, machine learning, and domain experience.
Machine learning libraries have helped along the first
two dimensions by providing modular implementations of
popular algorithms. However, implementing a pipeline
remains an iterative, tedious, and data-dependent task
as users have to experiment with different pipeline
designs. To make the pipeline development process
accessible to non-experts and more efficient for
experts, automated techniques can be used to
efficiently search for high performing pipelines with
little user intervention. The collection of techniques
and systems that automate this task are commonly termed
automated machine learning (AutoML).
Inspired by the success of software mining in areas such as code search, program synthesis, and program repair, we investigate the hypothesis that information mined from software artifacts can be used to build, improve interactions with, and address missing use cases of AutoML. In particular, I will present three systems -- AL, AMS, and Janus -- that make use of software artifacts. AL mines dynamic execution traces of a collection of programs that implement machine learning pipelines and uses these mined traces to learn to produce new pipelines. AMS mines documentation and program examples to automatically generate a search space for an AutoML tool by starting from a user-chosen set of API components. And Janus mines pipeline transformations from a collection of machine learning pipelines, which can be used to improve an input pipeline while producing a nearby variant. Jointly, these systems and their experimental results show that mining software artifacts can simplify AutoML systems, make their customization easier, and apply them to novel use cases.",
- notes = "Supervisor: Martin C. Rinard",
