AutoML from Software Engineering Perspective: Landscapes and ChallengesDistinguished Paper Award
Machine learning (ML) has been widely adopted in modern software, but the manual configuration of ML (e.g., hyper-parameter configuration) poses a significant challenge to software developers. Therefore, automated ML (AutoML), which seeks the optimal configuration of ML automatically, has received increasing attention from the software engineering community. However, to date, there is no comprehensive understanding of how AutoML is used by developers and what challenges developers encounter in using AutoML for software development. To fill this knowledge gap, we conduct the first study on understanding the use and challenges of AutoML from software developers’ perspective. We collect and analyze 1,554 AutoML downstream repositories, 769 AutoML-related Stack Overflow questions, and 1,437 relevant GitHub issues. The results suggest the increasing popularity of AutoML in a wide range of topics, but also the lack of relevant expertise. We manually identify specific challenges faced by developers for AutoML-enabled software. Based on the results, we derive a series of implications for AutoML framework selection, framework development, and research. Code scripts and datasets are publicly available.
Mon 15 MayDisplayed time zone: Hobart change
11:00 - 11:45 | SE for MLData and Tool Showcase Track / Technical Papers at Meeting Room 110 Chair(s): Sarah Nadi University of Alberta | ||
11:00 12mTalk | AutoML from Software Engineering Perspective: Landscapes and ChallengesDistinguished Paper Award Technical Papers Chao Wang Peking University, Zhenpeng Chen University College London, UK, Minghui Zhou Peking University Pre-print | ||
11:12 12mTalk | Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries Technical Papers Nima Shiri Harzevili York University, Jiho Shin York University, Junjie Wang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Song Wang York University, Nachiappan Nagappan Facebook | ||
11:24 6mTalk | DeepScenario: An Open Driving Scenario Dataset for Autonomous Driving System Testing Data and Tool Showcase Track Chengjie Lu Simula Research Laboratory and University of Oslo, Tao Yue Simula Research Laboratory, Shaukat Ali Simula Research Laboratory Pre-print | ||
11:30 6mTalk | NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python Data and Tool Showcase Track Ratnadira Widyasari Singapore Management University, Singapore, Zhou Yang Singapore Management University, Ferdian Thung Singapore Management University, Sheng Qin Sim Singapore Management University, Singapore, Fiona Wee Singapore Management University, Singapore, Camellia Lok Singapore Management University, Singapore, Jack Phan Singapore Management University, Singapore, Haodi Qi Singapore Management University, Singapore, Constance Tan Singapore Management University, Singapore, Qijin Tay Singapore Management University, Singapore, David Lo Singapore Management University | ||
11:36 6mTalk | PTMTorrent: A Dataset for Mining Open-source Pre-trained Model Packages Data and Tool Showcase Track Wenxin Jiang Purdue University, Nicholas Synovic Loyola University Chicago, Purvish Jajal Purdue University, Taylor R. Schorlemmer Purdue University, Arav Tewari Purdue University, Bhavesh Pareek Purdue University, George K. Thiruvathukal Loyola University Chicago and Argonne National Laboratory, James C. Davis Purdue University Pre-print | ||