Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Lio, Bruno Lepri, Andrea Passerini
Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable, or which explainer should be preferred in a given setting. In this survey we fill these gaps by devising a systematic experimental study, which tests twelve explainers on eight representative message-passing architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.
{"title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","authors":"Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Lio, Bruno Lepri, Andrea Passerini","doi":"10.1145/3696444","DOIUrl":"https://doi.org/10.1145/3696444","url":null,"abstract":"Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable, or which explainer should be preferred in a given setting. In this survey we fill these gaps by devising a systematic experimental study, which tests twelve explainers on eight representative message-passing architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"223 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, Digital Twin (DT) technology has emerged as a significant technological advancement. A digital twin is a digital representation of a physical asset that mirrors its data model, behaviour, and interactions with other physical assets. Digital Twin aims to achieve adaptability, seamless data integration, modelling, simulation, automation, and real-time data management. The primary goal of this paper is to explore the role of agents in DT implementations, seeking to understand their predominant usage scenarios and purposes. From our perspective, agents serving as intelligent entities play a role in realising the features of DTs. This paper also discusses the gaps in DT, highlights future directions, and analyses various technologies integrated with multi-agent systems technologies in DT implementations. Finally, the paper briefly discusses an overview of an architecture to implement a DT for smart agriculture with multi-agents.
{"title":"The Role of Multi-Agents in Digital Twin Implementation: Short Survey","authors":"Kalyani Yogeswaranathan, Rem Collier","doi":"10.1145/3697350","DOIUrl":"https://doi.org/10.1145/3697350","url":null,"abstract":"In recent years, Digital Twin (DT) technology has emerged as a significant technological advancement. A digital twin is a digital representation of a physical asset that mirrors its data model, behaviour, and interactions with other physical assets. Digital Twin aims to achieve adaptability, seamless data integration, modelling, simulation, automation, and real-time data management. The primary goal of this paper is to explore the role of agents in DT implementations, seeking to understand their predominant usage scenarios and purposes. From our perspective, agents serving as intelligent entities play a role in realising the features of DTs. This paper also discusses the gaps in DT, highlights future directions, and analyses various technologies integrated with multi-agent systems technologies in DT implementations. Finally, the paper briefly discusses an overview of an architecture to implement a DT for smart agriculture with multi-agents.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"1 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammad Tariq, Sohail Ahmad, Ahmad Jan Mian, Houbing Song
The envisioned sixth-generation (6G) networks anticipate robust support for diverse applications, including massive machine-type communications, ultra-reliable low-latency communications, and enhanced mobile broadband. Intelligent Reflecting Surfaces (IRS) have emerged as a key technology capable of intelligently reconfiguring wireless propagation environments, thereby enhancing overall network performance. Traditional optimization techniques face limitations in meeting the stringent performance requirements of 6G networks due to the intricate and dynamic nature of the wireless environment. Consequently, Deep Learning (DL) techniques are employed within the IRS framework to optimize wireless system performance. This paper provides a comprehensive survey of the latest research in DL-aided IRS models, covering optimal beamforming, resource allocation control, channel estimation and prediction, signal detection, and system deployment. The focus is on presenting promising solutions within the constraints of different hardware configurations. The survey explores challenges, opportunities, and open research issues in DL-aided IRS, considering emerging technologies such as digital twins (DTs), computer vision (CV), blockchain, network function virtualization (NFC), integrated sensing and communication (ISAC), software-defined networking (SDN), mobile edge computing (MEC), unmanned aerial vehicles (UAVs), and non-orthogonal multiple access (NOMA). Practical design issues associated with these enabling technologies are also discussed, providing valuable insights into the current state and future directions of this evolving field.
{"title":"Deep Learning Aided Intelligent Reflective Surfaces for 6G: A Survey","authors":"Muhammad Tariq, Sohail Ahmad, Ahmad Jan Mian, Houbing Song","doi":"10.1145/3696414","DOIUrl":"https://doi.org/10.1145/3696414","url":null,"abstract":"The envisioned sixth-generation (6G) networks anticipate robust support for diverse applications, including massive machine-type communications, ultra-reliable low-latency communications, and enhanced mobile broadband. Intelligent Reflecting Surfaces (IRS) have emerged as a key technology capable of intelligently reconfiguring wireless propagation environments, thereby enhancing overall network performance. Traditional optimization techniques face limitations in meeting the stringent performance requirements of 6G networks due to the intricate and dynamic nature of the wireless environment. Consequently, Deep Learning (DL) techniques are employed within the IRS framework to optimize wireless system performance. This paper provides a comprehensive survey of the latest research in DL-aided IRS models, covering optimal beamforming, resource allocation control, channel estimation and prediction, signal detection, and system deployment. The focus is on presenting promising solutions within the constraints of different hardware configurations. The survey explores challenges, opportunities, and open research issues in DL-aided IRS, considering emerging technologies such as digital twins (DTs), computer vision (CV), blockchain, network function virtualization (NFC), integrated sensing and communication (ISAC), software-defined networking (SDN), mobile edge computing (MEC), unmanned aerial vehicles (UAVs), and non-orthogonal multiple access (NOMA). Practical design issues associated with these enabling technologies are also discussed, providing valuable insights into the current state and future directions of this evolving field.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"23 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Álvaro Sobrinho, Matheus Vilarim, Amanda Barbosa, Edmar Candeia Gurjão, Danilo F. S. Santos, Dalton Valadares, Leandro Dias da Silva
Ensuring the security of vertical applications in fifth-generation (5G) mobile communication systems and previous generations is crucial. These systems must prioritize maintaining the confidentiality, integrity, and availability of services and data. Examples of vertical applications include smart cities, smart transportation, public services, Industry 4.0, smart grids, smart health, and smart agriculture. Each vertical application has specific security requirements and faces unique threats within the mobile network environment. Thus, it is essential to implement comprehensive and robust security measures. This approach helps minimize the attack surface and effectively manage risks. This survey thoroughly examines mobile networks and their security challenges in vertical applications, shedding light on associated threats and potential solutions. Our study considers the interplay between security considerations in 5G, legacy networks, and vertical applications. We emphasize the challenges, opportunities, and promising directions for future research in this field and the importance of securing vertical applications in the evolving landscape of mobile technology.
{"title":"Challenges and Opportunities in Mobile Network Security for Vertical Applications: A Survey","authors":"Álvaro Sobrinho, Matheus Vilarim, Amanda Barbosa, Edmar Candeia Gurjão, Danilo F. S. Santos, Dalton Valadares, Leandro Dias da Silva","doi":"10.1145/3696446","DOIUrl":"https://doi.org/10.1145/3696446","url":null,"abstract":"Ensuring the security of vertical applications in fifth-generation (5G) mobile communication systems and previous generations is crucial. These systems must prioritize maintaining the confidentiality, integrity, and availability of services and data. Examples of vertical applications include smart cities, smart transportation, public services, Industry 4.0, smart grids, smart health, and smart agriculture. Each vertical application has specific security requirements and faces unique threats within the mobile network environment. Thus, it is essential to implement comprehensive and robust security measures. This approach helps minimize the attack surface and effectively manage risks. This survey thoroughly examines mobile networks and their security challenges in vertical applications, shedding light on associated threats and potential solutions. Our study considers the interplay between security considerations in 5G, legacy networks, and vertical applications. We emphasize the challenges, opportunities, and promising directions for future research in this field and the importance of securing vertical applications in the evolving landscape of mobile technology.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"1 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaohan Zhang, Cen Zhang, Xinghua Li, Zhengjie Du, Bing Mao, Yuekang Li, Yaowen Zheng, Yeting Li, Li Pan, Yang Liu, Robert Deng
Communication protocols form the bedrock of our interconnected world, yet vulnerabilities within their implementations pose significant security threats. Recent developments have seen a surge in fuzzing-based research dedicated to uncovering these vulnerabilities within protocol implementations. However, there still lacks a systematic overview of protocol fuzzing for answering the essential questions such as what the unique challenges are, how existing works solve them, etc. To bridge this gap, we conducted a comprehensive investigation of related works from both academia and industry. Our study includes a detailed summary of the specific challenges in protocol fuzzing and provides a systematic categorization and overview of existing research efforts. Furthermore, we explore and discuss potential future research directions in protocol fuzzing.
{"title":"A Survey of Protocol Fuzzing","authors":"Xiaohan Zhang, Cen Zhang, Xinghua Li, Zhengjie Du, Bing Mao, Yuekang Li, Yaowen Zheng, Yeting Li, Li Pan, Yang Liu, Robert Deng","doi":"10.1145/3696788","DOIUrl":"https://doi.org/10.1145/3696788","url":null,"abstract":"Communication protocols form the bedrock of our interconnected world, yet vulnerabilities within their implementations pose significant security threats. Recent developments have seen a surge in fuzzing-based research dedicated to uncovering these vulnerabilities within protocol implementations. However, there still lacks a systematic overview of protocol fuzzing for answering the essential questions such as what the unique challenges are, how existing works solve them, etc. To bridge this gap, we conducted a comprehensive investigation of related works from both academia and industry. Our study includes a detailed summary of the specific challenges in protocol fuzzing and provides a systematic categorization and overview of existing research efforts. Furthermore, we explore and discuss potential future research directions in protocol fuzzing.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"68 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rahul Kumar, Manish Bhanu, João Mendes-Moreira, Joydeep Chandra
Spatio-temporal prediction tasks play a crucial role in facilitating informed decision-making through anticipatory insights. By accurately predicting future outcomes, the ability to strategize, preemptively address risks, and minimize their potential impact is enhanced. The precision in forecasting spatial and temporal patterns holds significant potential for optimizing resource allocation, land utilization, and infrastructure development. While existing review and survey papers predominantly focus on specific forecasting domains such as intelligent transportation, urban planning, pandemics, disease prediction, climate and weather forecasting, environmental data prediction, and agricultural yield projection, limited attention has been devoted to comprehensive surveys encompassing multiple objects concurrently. This paper addresses this gap by comprehensively analyzing techniques employed in traffic, pandemics, disease forecasting, climate and weather prediction, agricultural yield estimation, and environmental data prediction. Furthermore, it elucidates challenges inherent in spatio-temporal forecasting and outlines potential avenues for future research exploration.
{"title":"Spatio-Temporal Predictive Modeling Techniques for Different Domains: a Survey","authors":"Rahul Kumar, Manish Bhanu, João Mendes-Moreira, Joydeep Chandra","doi":"10.1145/3696661","DOIUrl":"https://doi.org/10.1145/3696661","url":null,"abstract":"Spatio-temporal prediction tasks play a crucial role in facilitating informed decision-making through anticipatory insights. By accurately predicting future outcomes, the ability to strategize, preemptively address risks, and minimize their potential impact is enhanced. The precision in forecasting spatial and temporal patterns holds significant potential for optimizing resource allocation, land utilization, and infrastructure development. While existing review and survey papers predominantly focus on specific forecasting domains such as intelligent transportation, urban planning, pandemics, disease prediction, climate and weather forecasting, environmental data prediction, and agricultural yield projection, limited attention has been devoted to comprehensive surveys encompassing multiple objects concurrently. This paper addresses this gap by comprehensively analyzing techniques employed in traffic, pandemics, disease forecasting, climate and weather prediction, agricultural yield estimation, and environmental data prediction. Furthermore, it elucidates challenges inherent in spatio-temporal forecasting and outlines potential avenues for future research exploration.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"64 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Financial technology (FinTech) is a field that uses artificial intelligence to automate financial services. One area of FinTech is stock analysis, which aims to predict future stock prices in order to develop investment strategies that maximize profits. Traditional methods of stock market prediction, such as time series analysis and machine learning, struggle to handle the non-linear, chaotic, and sudden changes in stock data and may not consider the interdependence between stocks. Recently, graph neural networks (GNNs) have been used in stock market forecasting to improve prediction accuracy by incorporating the interconnectedness of the market. GNNs can process non-Euclidean data in the form of a knowledge graph. However, financial knowledge graphs can have dynamic and complex interactions, which can be challenging for graph modeling technologies. This work presents a systematic review of graph based approaches for stock market forecasting. This review covers different types of stock analysis tasks (classification, regression, and stock recommendation), a generalized framework for solving these tasks, and a review of various features, datasets, graph models, and evaluation metrics used in the stock market. The results of various studies are analyzed, and future directions for research are highlighted.
{"title":"A Systematic Review on Graph Neural Network-based Methods for Stock Market Forecasting","authors":"Manali Patel, Krupa Jariwala, CHIRANJOY CHATTOPADHYAY","doi":"10.1145/3696411","DOIUrl":"https://doi.org/10.1145/3696411","url":null,"abstract":"Financial technology (FinTech) is a field that uses artificial intelligence to automate financial services. One area of FinTech is stock analysis, which aims to predict future stock prices in order to develop investment strategies that maximize profits. Traditional methods of stock market prediction, such as time series analysis and machine learning, struggle to handle the non-linear, chaotic, and sudden changes in stock data and may not consider the interdependence between stocks. Recently, graph neural networks (GNNs) have been used in stock market forecasting to improve prediction accuracy by incorporating the interconnectedness of the market. GNNs can process non-Euclidean data in the form of a knowledge graph. However, financial knowledge graphs can have dynamic and complex interactions, which can be challenging for graph modeling technologies. This work presents a systematic review of graph based approaches for stock market forecasting. This review covers different types of stock analysis tasks (classification, regression, and stock recommendation), a generalized framework for solving these tasks, and a review of various features, datasets, graph models, and evaluation metrics used in the stock market. The results of various studies are analyzed, and future directions for research are highlighted.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"26 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kai Huang, Zhengzi Xu, Su Yang, Hongyu Sun, Xuejun Li, Zheng Yan, Yuqing Zhang
With the rapid development and large-scale popularity of program software, modern society increasingly relies on software systems. However, the problems exposed by software have also come to the fore. The software bug has become an important factor troubling developers. In this context, Automated Program Repair (APR) techniques have emerged, aiming to automatically fix software bug problems and reduce manual debugging work. In particular, benefiting from the advances in deep learning, numerous learning-based APR techniques have emerged in recent years, which also bring new opportunities for APR research. To give researchers a quick overview of APR techniques’ complete development and future opportunities, we review the evolution of APR techniques and discuss in depth the latest advances in APR research. In this paper, the development of APR techniques is introduced in terms of four different patch generation schemes: search-based, constraint-based, template-based, and learning-based. Moreover, we propose a uniform set of criteria to review and compare each APR tool and then discuss the current state of APR development. Finally, we analyze current challenges and future directions, especially highlighting the critical opportunities that large language models bring to APR research.
{"title":"Evolving Paradigms in Automated Program Repair: Taxonomy, Challenges, and Opportunities","authors":"Kai Huang, Zhengzi Xu, Su Yang, Hongyu Sun, Xuejun Li, Zheng Yan, Yuqing Zhang","doi":"10.1145/3696450","DOIUrl":"https://doi.org/10.1145/3696450","url":null,"abstract":"With the rapid development and large-scale popularity of program software, modern society increasingly relies on software systems. However, the problems exposed by software have also come to the fore. The software bug has become an important factor troubling developers. In this context, Automated Program Repair (APR) techniques have emerged, aiming to automatically fix software bug problems and reduce manual debugging work. In particular, benefiting from the advances in deep learning, numerous learning-based APR techniques have emerged in recent years, which also bring new opportunities for APR research. To give researchers a quick overview of APR techniques’ complete development and future opportunities, we review the evolution of APR techniques and discuss in depth the latest advances in APR research. In this paper, the development of APR techniques is introduced in terms of four different patch generation schemes: search-based, constraint-based, template-based, and learning-based. Moreover, we propose a uniform set of criteria to review and compare each APR tool and then discuss the current state of APR development. Finally, we analyze current challenges and future directions, especially highlighting the critical opportunities that large language models bring to APR research.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"12 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Francisco Silva, Hélder P. Oliveira, Tania Pereira
The large gap between the generalization level of state-of-the-art machine learning and human learning systems calls for the development of artificial intelligence (AI) models that are truly inspired by human cognition. In tasks related to image analysis, searching for pixel-level regularities has reached a power of information extraction still far from what humans capture with image-based observations. This leads to poor generalization when even small shifts occur at the level of the observations. We explore a perspective on this problem that is directed to learning the generative process with causality-related foundations, using models capable of combining symbolic manipulation, probabilistic reasoning and pattern recognition abilities. We briefly review and explore connections of research from machine learning, cognitive science and related fields of human behavior to support our perspective for the direction to more robust and human-like artificial learning systems.
{"title":"Causal representation learning through higher-level information extraction","authors":"Francisco Silva, Hélder P. Oliveira, Tania Pereira","doi":"10.1145/3696412","DOIUrl":"https://doi.org/10.1145/3696412","url":null,"abstract":"The large gap between the generalization level of state-of-the-art machine learning and human learning systems calls for the development of artificial intelligence (AI) models that are truly inspired by human cognition. In tasks related to image analysis, searching for pixel-level regularities has reached a power of information extraction still far from what humans capture with image-based observations. This leads to poor generalization when even small shifts occur at the level of the observations. We explore a perspective on this problem that is directed to learning the generative process with causality-related foundations, using models capable of combining symbolic manipulation, probabilistic reasoning and pattern recognition abilities. We briefly review and explore connections of research from machine learning, cognitive science and related fields of human behavior to support our perspective for the direction to more robust and human-like artificial learning systems.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"287 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiuting Ge, Chunrong Fang, Xuanye Li, Weisong Sun, Daoyuan Wu, Juan Zhai, Shang-Wei Lin, Zhihong Zhao, Yang Liu, Zhenyu Chen
Actionable Warning Identification (AWI) plays a crucial role in improving the usability of static code analyzers. With recent advances in Machine Learning (ML), various approaches have been proposed to incorporate ML techniques into AWI. These ML-based AWI approaches, benefiting from ML’s strong ability to learn subtle and previously unseen patterns from historical data, have demonstrated superior performance. However, a comprehensive overview of these approaches is missing, which could hinder researchers and practitioners from understanding the current process and discovering potential for future improvement in the ML-based AWI community. In this paper, we systematically review the state-of-the-art ML-based AWI approaches. First, we employ a meticulous survey methodology and gather 51 primary studies from 2000/01/01 to 2023/09/01. Then, we outline a typical ML-based AWI workflow, including warning dataset preparation, preprocessing, AWI model construction, and evaluation stages. In such a workflow, we categorize ML-based AWI approaches based on the warning output format. Besides, we analyze the key techniques used in each stage, along with their strengths, weaknesses, and distribution. Finally, we provide practical research directions for future ML-based AWI approaches, focusing on aspects like data improvement (e.g., enhancing the warning labeling strategy) and model exploration (e.g., exploring large language models for AWI).
可执行警告识别（AWI）在提高静态代码分析器的可用性方面发挥着至关重要的作用。随着机器学习（ML）技术的不断进步，人们提出了各种将 ML 技术融入 AWI 的方法。这些基于 ML 的 AWI 方法得益于 ML 强大的从历史数据中学习微妙和以前未见模式的能力，表现出了卓越的性能。然而，目前还缺少对这些方法的全面概述，这可能会妨碍研究人员和从业人员了解当前的进程，并发现基于 ML 的 AWI 社区未来的改进潜力。在本文中，我们系统地回顾了最先进的基于 ML 的 AWI 方法。首先，我们采用细致的调查方法，收集了从 2000/01/01 到 2023/09/01 的 51 项主要研究。然后，我们概述了基于 ML 的典型 AWI 工作流程，包括预警数据集准备、预处理、AWI 模型构建和评估阶段。在这样的工作流程中，我们根据预警输出格式对基于 ML 的预警识别方法进行了分类。此外，我们还分析了每个阶段使用的关键技术及其优缺点和分布情况。最后，我们为未来基于 ML 的预警识别方法提供了实用的研究方向，重点关注数据改进（如增强预警标记策略）和模型探索（如探索用于预警识别的大型语言模型）等方面。
{"title":"Machine Learning for Actionable Warning Identification: A Comprehensive Survey","authors":"Xiuting Ge, Chunrong Fang, Xuanye Li, Weisong Sun, Daoyuan Wu, Juan Zhai, Shang-Wei Lin, Zhihong Zhao, Yang Liu, Zhenyu Chen","doi":"10.1145/3696352","DOIUrl":"https://doi.org/10.1145/3696352","url":null,"abstract":"Actionable Warning Identification (AWI) plays a crucial role in improving the usability of static code analyzers. With recent advances in Machine Learning (ML), various approaches have been proposed to incorporate ML techniques into AWI. These ML-based AWI approaches, benefiting from ML’s strong ability to learn subtle and previously unseen patterns from historical data, have demonstrated superior performance. However, a comprehensive overview of these approaches is missing, which could hinder researchers and practitioners from understanding the current process and discovering potential for future improvement in the ML-based AWI community. In this paper, we systematically review the state-of-the-art ML-based AWI approaches. First, we employ a meticulous survey methodology and gather 51 primary studies from 2000/01/01 to 2023/09/01. Then, we outline a typical ML-based AWI workflow, including warning dataset preparation, preprocessing, AWI model construction, and evaluation stages. In such a workflow, we categorize ML-based AWI approaches based on the warning output format. Besides, we analyze the key techniques used in each stage, along with their strengths, weaknesses, and distribution. Finally, we provide practical research directions for future ML-based AWI approaches, focusing on aspects like data improvement (e.g., enhancing the warning labeling strategy) and model exploration (e.g., exploring large language models for AWI).","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"23 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：