ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal
Wed 17 Apr 2024 14:45 - 15:00 at Sophia de Mello Breyner Andresen - Analytics & AI Chair(s): Lingming Zhang

Deep Learning (DL) libraries have significantly impacted various domains in computer science over the last decade. However, developers often face challenges when using DL APIs, as the development paradigm of DL applications differs greatly from traditional software development. Existing studies on API misuse mainly focus on traditional software, leaving a gap in understanding API misuse within DL APIs. To address this gap, we present the first comprehensive study of DL API misuse in TensorFlow and PyTorch. Specifically, we first collect a dataset of 4,224 commits from the top 200 most-starred projects using these two libraries and manually identified 891 API misuses. We then investigate the characteristics of these misuses from three perspectives, i.e., types, root causes, and symptoms. We have also conducted an evaluation to assess the effectiveness of the current state-of-the-art API misuse detector on our 891 confirmed API misuses. Our results confirmed that the SOTA API misuse detector is ineffective for detecting DL API misuses. To address the limitations of existing API misuse detection for DL APIs, we propose LLMAPIDet, which leverages Large Language Models (LLMs) for DL API misuse detection and repair. We build LLMAPIDet by prompt-tuning a chain of ChatGPT prompts on 600 out of 891 confirmed API misuses and reserve the rest 291 API misuses as the testing dataset. Our evaluation shows thatLLMAPIDet can detect 48 out of the 291 DL API misuses while none of them can be detected by the existing API misuse detector. We further evaluate LLMAPIDet on the latest versions of 10 GitHub projects. The evaluation shows that LLMAPIDet can identify 119 previously unknown API misuses and successfully fix 46 of them.

Wed 17 Apr

Displayed time zone: Lisbon change

14:00 - 15:30
Analytics & AIResearch Track / Journal-first Papers at Sophia de Mello Breyner Andresen
Chair(s): Lingming Zhang University of Illinois at Urbana-Champaign
14:00
15m
Talk
DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection
Research Track
Youcef REMIL INSA Lyon, INFOLOGIC, Anes Bendimerad Infologic, Romain Mathonat Infologic, Chedy raissi Ubisoft, Mehdi Kaytoue Infologic
14:15
15m
Talk
DivLog: Log Parsing with Prompt Enhanced In-Context Learning
Research Track
Junjielong Xu The Chinese University of Hong Kong, Shenzhen, Ruichun Yang The Chinese University of Hong Kong, Shenzhen, Yintong Huo The Chinese University of Hong Kong, Chengyu Zhang ETH Zurich, Pinjia He Chinese University of Hong Kong, Shenzhen
14:30
15m
Talk
Where is it? Tracing the Vulnerability-relevant Files from Vulnerability Reports
Research Track
Jiamou Sun CSIRO's Data61, Jieshan Chen CSIRO's Data61, Zhenchang Xing CSIRO's Data61, Qinghua Lu Data61, CSIRO, Xiwei (Sherry) Xu Data61, CSIRO, Liming Zhu CSIRO’s Data61
14:45
15m
Talk
Demystifying and Detecting Misuses of Deep Learning APIs
Research Track
Moshi Wei York University, Nima Shiri Harzevili York University, Yuekai Huang Institute of Software, Chinese Academy of Sciences, Jinqiu Yang Concordia University, Junjie Wang Institute of Software, Chinese Academy of Sciences, Song Wang York University
15:00
7m
Talk
Toward Understanding Deep Learning Framework Bugs
Journal-first Papers
Junjie Chen Tianjin University, Yihua Liang College of Intelligence and Computing, Tianjin University, Qingchao Shen Tianjin University, Jiajun Jiang Tianjin University, Shuochuan Li College of Intelligence and Computing, Tianjin University
15:07
7m
Talk
Fair Enough: Searching for Sufficient Measures of Fairness
Journal-first Papers
Suvodeep Majumder North Carolina State University, Joymallya Chakraborty Amazon.com, Gina Bai North Carolina State University, Kathryn Stolee North Carolina State University, Tim Menzies North Carolina State University
DOI Pre-print
15:14
7m
Talk
Representation Learning for Stack Overflow Posts: How Far are We?
Journal-first Papers
Junda He Singapore Management University, Xin Zhou Singapore Management University, Singapore, Bowen Xu North Carolina State University, Ting Zhang Singapore Management University, Kisub Kim Singapore Management University, Singapore, Zhou Yang Singapore Management University, Ferdian Thung Singapore Management University, Ivana Clairine Irsan Singapore Management University, David Lo Singapore Management University
15:21
7m
Talk
Journal First: Learning from Very Little Data: On the Value of Landscape Analysis for Predicting Software Project Health)
Journal-first Papers
Andre Lustosa North Carolina State University, Tim Menzies North Carolina State University
DOI Pre-print