Write a Blog >>
ICSE 2022
Sun 8 - Fri 27 May 2022
Mon 9 May 2022 20:10 - 20:15 at ICSE room 4-even hours - Search-Based Software Engineering 2 Chair(s): Ali Ouni
Tue 10 May 2022 05:05 - 05:10 at ICSE room 2-odd hours - Search-Based Software Engineering 1 Chair(s): Ruchika Malhotra

Neural program embeddings have demonstrated considerable promise in a range of program analysis tasks, including clone identification, program repair, code completion, and program synthesis. However, most existing methods generate neural program embeddings directly from the program source codes, by learning from features such as tokens, abstract syntax trees, and control flow graphs.

This paper takes a fresh look at how to improve program embeddings by leveraging compiler intermediate representation (IR). We first demonstrate simple yet highly effective methods for enhancing embedding quality by training embedding models alongside source code and LLVM IR generated by default optimization levels (e.g., -O2). We then introduce IRGen, a framework based on genetic algorithms (GA), to identify (near-)optimal sequences of optimization flags that can significantly improve embedding quality.

We use IRGen to find optimal sequences of LLVM optimization flags by performing GA on source code datasets. We then extend a popular code embedding model, CodeCMR, by adding a new objective based on triplet loss to enable a joint learning over source code and LLVM IR. When CodeCMR was trained with source code and LLVM IRs optimized by findings of IRGen, the embedding quality was significantly improved, outperforming the state-of-the-art model, CodeBERT, which was trained only with source code. Our augmented CodeCMR also outperformed CodeCMR trained over source code and IR optimized with default optimization levels. We investigate the properties of optimization flags that increase embedding quality, demonstrate IRGen’s generalization in boosting other embedding models, and establish IRGen’s use in settings with extremely limited training data. Our research and findings demonstrate that a low-cost addition to modern neural code embedding models can provide an universal and highly effective enhancement.

Mon 9 May

Displayed time zone: Eastern Time (US & Canada) change

20:00 - 21:00
Search-Based Software Engineering 2NIER - New Ideas and Emerging Results / Technical Track at ICSE room 4-even hours
Chair(s): Ali Ouni ETS Montreal, University of Quebec
20:00
5m
Talk
A Black Box Technique to Reduce Energy Consumption of Android Apps
NIER - New Ideas and Emerging Results
Abdul Ali Bangash University of Alberta, Canada, Karim Ali University of Alberta, Abram Hindle University of Alberta
Pre-print Media Attached
20:05
5m
Talk
Fairness-aware Configuration of Machine Learning Libraries
Technical Track
Saeid Tizpaz-Niari University of Texas at El Paso, Ashish Kumar , Gang Tan Pennsylvania State University, Ashutosh Trivedi University of Colorado Boulder
DOI Pre-print Media Attached
20:10
5m
Talk
Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings
Technical Track
Zongjie Li The Hong Kong University of Science and Technology, Pingchuan Ma HKUST, Huaijin Wang , Shuai Wang Hong Kong University of Science and Technology, Qiyi Tang Tencent Security Keen Lab, Sen Nie Keen Security Lab, Tencent, Shi Wu Tencent Security Keen Lab
DOI Pre-print Media Attached
20:15
5m
Talk
Control Parameters Considered Harmful: Detecting Range Specification Bugs in Drone Configuration Modules via Learning-Guided Search
Technical Track
Ruidong Han Xidian University, Chao Yang Xidian University, Siqi Ma The University of New South Wales Canberra, Jianfeng Ma Xidian University, Cong Sun Xidian University, Juanru Li Shanghai Jiao Tong University, Elisa Bertino Purdue University
DOI Pre-print Media Attached
20:20
5m
Talk
Search-based Diverse Sampling from Real-world Software Product Lines
Technical Track
Yi Xiang South China University of Technology, Han Huang South China University of Technology, Yuren Zhou School of Data and Computer Science, Sun Yat-sen University, Sizhe Li South China University of Technology, Chuan Luo Beihang University, Qingwei Lin Microsoft Research, Miqing Li University of Birmingham, Xiaowei Yang South China University of Technology
DOI Pre-print Media Attached
20:25
5m
Talk
Code Search based on Context-aware Code Translation
Technical Track
Weisong Sun State Key Laboratory for Novel Software Technology, Nanjing University, Chunrong Fang Nanjing University, Yuchen Chen Nanjing University, Guanhong Tao Purdue University, USA, Tingxu Han Nanjing University, Quanjun Zhang Nanjing University
Pre-print Media Attached

Tue 10 May

Displayed time zone: Eastern Time (US & Canada) change

05:00 - 06:00
Search-Based Software Engineering 1Technical Track at ICSE room 2-odd hours
Chair(s): Ruchika Malhotra Delhi Technological University
05:00
5m
Talk
Efficient Online Testing for DNN-Enabled Systems using Surrogate-Assisted and Many-Objective OptimizationDistinguished Paper Award
Technical Track
Fitash Ul Haq University of Luxembourg, Donghwan Shin University of Luxembourg, Lionel Briand University of Luxembourg; University of Ottawa
Pre-print Media Attached
05:05
5m
Talk
Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings
Technical Track
Zongjie Li The Hong Kong University of Science and Technology, Pingchuan Ma HKUST, Huaijin Wang , Shuai Wang Hong Kong University of Science and Technology, Qiyi Tang Tencent Security Keen Lab, Sen Nie Keen Security Lab, Tencent, Shi Wu Tencent Security Keen Lab
DOI Pre-print Media Attached
05:10
5m
Talk
Control Parameters Considered Harmful: Detecting Range Specification Bugs in Drone Configuration Modules via Learning-Guided Search
Technical Track
Ruidong Han Xidian University, Chao Yang Xidian University, Siqi Ma The University of New South Wales Canberra, Jianfeng Ma Xidian University, Cong Sun Xidian University, Juanru Li Shanghai Jiao Tong University, Elisa Bertino Purdue University
DOI Pre-print Media Attached
05:15
5m
Talk
Search-based Diverse Sampling from Real-world Software Product Lines
Technical Track
Yi Xiang South China University of Technology, Han Huang South China University of Technology, Yuren Zhou School of Data and Computer Science, Sun Yat-sen University, Sizhe Li South China University of Technology, Chuan Luo Beihang University, Qingwei Lin Microsoft Research, Miqing Li University of Birmingham, Xiaowei Yang South China University of Technology
DOI Pre-print Media Attached
05:20
5m
Talk
PropR: Property-Based Automatic Program Repair
Technical Track
Matthías Páll Gissurarson Chalmers University of Technology, Sweden, Leonhard Applis Delft University of Technology, Annibale Panichella Delft University of Technology, Arie van Deursen Delft University of Technology, Netherlands, Dave Sands Chalmers
DOI Pre-print Media Attached
05:25
5m
Talk
Code Search based on Context-aware Code Translation
Technical Track
Weisong Sun State Key Laboratory for Novel Software Technology, Nanjing University, Chunrong Fang Nanjing University, Yuchen Chen Nanjing University, Guanhong Tao Purdue University, USA, Tingxu Han Nanjing University, Quanjun Zhang Nanjing University
Pre-print Media Attached

Information for Participants
Mon 9 May 2022 20:00 - 21:00 at ICSE room 4-even hours - Search-Based Software Engineering 2 Chair(s): Ali Ouni
Info for room ICSE room 4-even hours:

Click here to go to the room on Midspace

Tue 10 May 2022 05:00 - 06:00 at ICSE room 2-odd hours - Search-Based Software Engineering 1 Chair(s): Ruchika Malhotra
Info for room ICSE room 2-odd hours:

Click here to go to the room on Midspace