Chen Zhi

Chen Zhi

Auto-generated profile, based on publicly available information

Chen Zhi

Zhejiang University, Ningbo, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2024
Verified
Conference Paper
Open access
YCYinghao Chen
Yinghao Chen
ZHZehao Hu
Zehao Hu
CZChen Zhi
Chen Zhi
JHJunxiao Han
Junxiao Han
Shuguang DengShuguang Deng
Shuguang Deng
JYJianwei Yin
Jianwei Yin
Unit testing is an essential yet frequently arduous task. Various automated unit test generation tools have been introduced to mitigate this challenge. Notably, methods based on large language models (LLMs) have garnered considerable attention and exhibited promising results in recent years. Nevertheless, LLM-based tools encounter limitations in generating accurate unit tests. This paper presents ChatUniTest, an LLM-based automated unit test generation framework. ChatUniTest incorporates an adaptive focal context mechanism to encompass valuable context in prompts and adheres to a generation-validation-repair mechanism to rectify errors in generated unit tests. Subsequently, we have developed ChatUniTest Core, a common library that implements core workflow, complemented by the ChatUniTest Toolchain, a suite of seamlessly integrated tools enhancing the capabilities of ChatUniTest. Our effectiveness evaluation reveals that ChatUniTest outperforms TestSpark and EvoSuite in half of the evaluated projects, achieving the highest overall line coverage. Furthermore, insights from our user study affirm that ChatUniTest delivers substantial value to various stakeholders in the software testing domain. ChatUniTest is available at https://github.com/ZJU-ACES-ISE/ChatUniTest, and the demo video is available at https://www.youtube.com/watch?v=GmfxQUqm2ZQ.

11 July 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
ZCZhenqian Chen
Zhenqian Chen
XZXinkui Zhao
Xinkui Zhao
CZChen Zhi
Chen Zhi
JYJianwei Yin
Jianwei Yin
Deep learning tasks (DLT) include training and inference tasks, where training DLTs have requirements on minimizing average job completion time (JCT) and inference tasks need sufficient GPUs to meet real-time performance. Unfortunately, existing work separately deploys multi-tenant training and inference GPU cluster, leading to the high JCT of training DLTs with limited GPUs when the inference cluster is under insufficient GPU utilization due to the periodic inference workload. DeepBoot solves the challenges by utilizing idle GPUs in the inference cluster for the training DLTs. Specifically, 1) DeepBoot designs adaptive task scaling (ATS) algorithm to allocate GPUs in the training and inference clusters for training DLTs and minimize the performance loss when reclaiming inference GPUs. 2) DeepBoot implements auto-fast elastic (AFE) training based on Pollux to reduce the restart overhead by inference GPU reclaiming. Our implementation on the testbed and large-scale simulation in Microsoft deep learning workload shows that DeepBoot can achieve 32% and 38% average JCT reduction respectively compared with the scheduler without utilizing idle GPUs in the inference cluster.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZQZhen Qin
Zhen Qin
FCFeiyi Chen
Feiyi Chen
CZChen Zhi
Chen Zhi
XYXueqiang Yan
Xueqiang Yan
Shuguang DengShuguang Deng
Shuguang Deng
Existing approaches defend against backdoor attacks in federated learning (FL) mainly through a) mitigating the impact of infected models, or b) excluding infected models. The former negatively impacts model accuracy, while the latter usually relies on globally clear boundaries between benign and infected model updates. However, in reality, model updates can easily become mixed and scattered throughout due to the diverse distributions of local data. This work focuses on excluding infected models in FL. Unlike previous perspectives from a global view, we propose Snowball, a novel anti-backdoor FL framework through bidirectional elections from an individual perspective inspired by one principle deduced by us and two principles in FL and deep learning. It is characterized by a) bottom-up election, where each candidate model update votes to several peer ones such that a few model updates are elected as selectees for aggregation; and b) top-down election, where selectees progressively enlarge themselves through picking up from the candidates. We compare Snowball with state-of-the-art defenses to backdoor attacks in FL on five real-world datasets, demonstrating its superior resistance to backdoor attacks and slight impact on the accuracy of the global model.

27 October 2024
Verified
Conference Paper
Open access
GLGuochang Li
Guochang Li
CZChen Zhi
Chen Zhi
JCJialiang Chen
Jialiang Chen
JHJunxiao Han
Junxiao Han
Shuguang DengShuguang Deng
Shuguang Deng
Automated Program Repair (APR) aims to fix bugs by generating patches. And existing work has demonstrated that "pre-training and fine-tuning" paradigm enables Large Language Models (LLMs) improve fixing capabilities on APR. However, existing work mainly focuses on Full-Model Fine-Tuning (FMFT) for APR and limited research has been conducted on the execution-based evaluation of Parameter-Efficient Fine-Tuning (PEFT) for APR. Comparing to FMFT, PEFT can reduce computing resource consumption without compromising performance and has been widely adopted to other software engineering tasks. To fill this gap, we enhance the existing APR dataset by employing prompt engineering to create an instruction dataset, APR-Instruction, at first. Secondly, we fine-tune four pre-trained LLMs using four different PEFT methods with APR-Instruction. The best fine-tuned model fixes 58% more bugs than the state-of-the-art LLM-based APR techniques. The results also show that (IA)3 improves the creativity of LLMs more effectively through fine-tuning and achieves the highest fixing capability compared to the other three PEFT methods. Thirdly, we explore the optimal configuration of PEFT hyperparameters, and assess the impact of instruction dataset size, showing that a larger number of parameters and a larger training dataset do not necessarily result in better performance for PEFT. Lastly, we analyze peak memory usage and trainable parameters to show the efficiency of PEFT. This work provides a comprehensive exploration of PEFT on APR and suggests potentially promising directions for extension to other software engineering downstream tasks. APR-Instruction, PEFT weights, and the fine-tuning code are publicly available as open-source resources.

31 December 2021 in Automated Software Engineering
Verified
Journal Article
Closed access
PDF file
CZChen Zhi
Chen Zhi
Shuguang DengShuguang Deng
Shuguang Deng
JHJunxiao Han
Junxiao Han
JYJianwei Yin
Jianwei Yin

24 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
KZKangjia Zhao
Kangjia Zhao
JSJiahui Song
Jiahui Song
LSLeigang Sha
Leigang Sha
HSHaozhan Shen
Haozhan Shen
ZCZhi Chen
Zhi Chen
JYJianwei Yin
Jianwei Yin
Nowadays, research on GUI agents is a hot topic in the AI community. However, current research focuses on GUI task automation, limiting the scope of applications in various GUI scenarios. In this paper, we propose a formalized and comprehensive environment to evaluate the entire process of automated GUI Testing (GTArena), offering a fair, standardized environment for consistent operation of diverse multimodal large language models. We divide the testing process into three key subtasks: test intention generation, test task execution, and GUI defect detection, and construct a benchmark dataset based on these to conduct a comprehensive evaluation. It evaluates the performance of different models using three data types: real mobile applications, mobile applications with artificially injected defects, and synthetic data, thoroughly assessing their capabilities in this relevant task. Additionally, we propose a method that helps researchers explore the correlation between the performance of multimodal language large models in specific scenarios and their general capabilities in standard benchmark tests. Experimental results indicate that even the most advanced models struggle to perform well across all sub-tasks of automated GUI Testing, highlighting a significant gap between the current capabilities of Autonomous GUI Testing and its practical, real-world applicability. This gap provides guidance for the future direction of GUI Agent development. Our code is available at https://github.com/ZJU-ACES-ISE/ChatUITest.