Pub Date : 2024-11-01DOI: 10.1109/TSC.2024.3489435
Tao Ouyang;Xu Chen;Liekang Zeng;Zhi Zhou
To meet the stringent requirement of edge intelligence applications, resource-constrained devices can offload their task to nearby resource-rich devices. Resource awareness, as a prime prerequisite for offloading decision-making, is critical for achieving efficient collaborative computation performance. Although major works have explored computation offloading in dynamic edge environments, the impact of fresh resource information perception has not been formally investigated. To bridge the gap, we design a cost-aware edge resource probing (CERP) framework for infrastructure-free edge computing, where a task device self-organizes its resource probing to enable informed computation offloading. We first formulate the joint optimization of device probing and offloading as a multi-stage optimal stopping problem and derive a multi-threshold-based optimal strategy with theoretical guarantees. Accordingly, we devise a data-driven layered learning mechanism to handle more complex real-world scenarios. The layered learning enables the task device to adaptively learn the optimal probing sequence and decision thresholds on the fly, aiming to strike a good balance between the gain of choosing the best edge device and the accumulated cost of deep resource probing. To further boost its learning efficiency, we replace the $epsilon$ -greedy method with a tailored UCB-based adaptive exploration scheme in layered learning, thus better navigating the exploration and exploitation trade-off during probing processes. Finally, we conduct a thorough performance evaluation of the proposed CERP schemes using both extensive numerical simulations and realistic system prototype implementation, which demonstrate the superior performance of CERP in diverse application scenarios.
{"title":"Cost-Aware Dispersed Resource Probing and Offloading at the Edge: A User-Centric Online Layered Learning Approach","authors":"Tao Ouyang;Xu Chen;Liekang Zeng;Zhi Zhou","doi":"10.1109/TSC.2024.3489435","DOIUrl":"10.1109/TSC.2024.3489435","url":null,"abstract":"To meet the stringent requirement of edge intelligence applications, resource-constrained devices can offload their task to nearby resource-rich devices. Resource awareness, as a prime prerequisite for offloading decision-making, is critical for achieving efficient collaborative computation performance. Although major works have explored computation offloading in dynamic edge environments, the impact of fresh resource information perception has not been formally investigated. To bridge the gap, we design a cost-aware edge resource probing (CERP) framework for infrastructure-free edge computing, where a task device self-organizes its resource probing to enable informed computation offloading. We first formulate the joint optimization of device probing and offloading as a multi-stage optimal stopping problem and derive a multi-threshold-based optimal strategy with theoretical guarantees. Accordingly, we devise a data-driven layered learning mechanism to handle more complex real-world scenarios. The layered learning enables the task device to adaptively learn the optimal probing sequence and decision thresholds on the fly, aiming to strike a good balance between the gain of choosing the best edge device and the accumulated cost of deep resource probing. To further boost its learning efficiency, we replace the \u0000<inline-formula><tex-math>$epsilon$</tex-math></inline-formula>\u0000-greedy method with a tailored UCB-based adaptive exploration scheme in layered learning, thus better navigating the exploration and exploitation trade-off during probing processes. Finally, we conduct a thorough performance evaluation of the proposed CERP schemes using both extensive numerical simulations and realistic system prototype implementation, which demonstrate the superior performance of CERP in diverse application scenarios.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3270-3285"},"PeriodicalIF":5.5,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142563110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1109/TSC.2024.3489437
Haibo Liu;Jianfeng Lu;Xiong Wang;Chen Wang;Riheng Jia;Minglu Li
Although federated learning (FL) enables collaborative training across multiple data silos in a privacy-protected manner, naively minimizing the aggregated loss to facilitate an efficient federation may compromise its fairness. Many efforts have been devoted to maintaining similar average accuracy across clients by reweighing the loss function while clients’ potential contributions are largely ignored. This, however, is often detrimental since treating all clients equally will harm the interests of those clients with more contribution. To tackle this issue, we introduce utopian fairness to expound the relationship between individual earning and collaborative productivity, and propose Fed erated- U to P ia (FedUP), a novel FL framework that balances both efficient collaboration and fair aggregation. For the distributed collaboration, we model the training process among strategic clients as a supermodular game, which facilitates a rational incentive design through the optimal reward. As for the model aggregation, we design a weight attention mechanism to compute the fair aggregation weights by minimizing the performance bias among heterogeneous clients. Particularly, we utilize the alternating optimization theory to bridge the gap between collaboration efficiency and utopian fairness, and theoretically prove that FedUP has fair model performance with fast-rate training convergence. Extensive experiments using both synthetic and real datasets demonstrate the superiority of FedUP.
{"title":"FedUP: Bridging Fairness and Efficiency in Cross-Silo Federated Learning","authors":"Haibo Liu;Jianfeng Lu;Xiong Wang;Chen Wang;Riheng Jia;Minglu Li","doi":"10.1109/TSC.2024.3489437","DOIUrl":"10.1109/TSC.2024.3489437","url":null,"abstract":"Although federated learning (FL) enables collaborative training across multiple data silos in a privacy-protected manner, naively minimizing the aggregated loss to facilitate an efficient federation may compromise its fairness. Many efforts have been devoted to maintaining similar average accuracy across clients by reweighing the loss function while clients’ potential contributions are largely ignored. This, however, is often detrimental since treating all clients equally will harm the interests of those clients with more contribution. To tackle this issue, we introduce utopian fairness to expound the relationship between individual earning and collaborative productivity, and propose \u0000<underline>Fed</u>\u0000erated-\u0000<underline>U</u>\u0000to\u0000<underline>P</u>\u0000ia (FedUP), a novel FL framework that balances both efficient collaboration and fair aggregation. For the distributed collaboration, we model the training process among strategic clients as a supermodular game, which facilitates a rational incentive design through the optimal reward. As for the model aggregation, we design a weight attention mechanism to compute the fair aggregation weights by minimizing the performance bias among heterogeneous clients. Particularly, we utilize the alternating optimization theory to bridge the gap between collaboration efficiency and utopian fairness, and theoretically prove that FedUP has fair model performance with fast-rate training convergence. Extensive experiments using both synthetic and real datasets demonstrate the superiority of FedUP.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3672-3684"},"PeriodicalIF":5.5,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142563109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1109/tsc.2024.3489433
Weipeng Cao, Jiongjiong Gu, Zhong Ming, Zhiyuan Cai, Yuzhao Wang, Changping Ji, Zhijiao Xiao, Yuhong Feng, Ye Liu, Liang-Jie Zhang
{"title":"Flexible Computing: A New Framework for Improving Resource Allocation and Scheduling in Elastic Computing","authors":"Weipeng Cao, Jiongjiong Gu, Zhong Ming, Zhiyuan Cai, Yuzhao Wang, Changping Ji, Zhijiao Xiao, Yuhong Feng, Ye Liu, Liang-Jie Zhang","doi":"10.1109/tsc.2024.3489433","DOIUrl":"https://doi.org/10.1109/tsc.2024.3489433","url":null,"abstract":"","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"22 1","pages":""},"PeriodicalIF":8.1,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cardiovascular diseases (CVDs) are the primary cause of mortality worldwide. The healthcare sector in India currently shows promise for substantial changes, specifically in the utilization and importance of the Internet of Medical Things (IoMT). Edge computing is necessary to make the IoMT more scalable, portable, reliable, and responsive. Security and privacy concerns impede the development and deployment of IoMT devices. The technology of blockchain can resolve security and privacy concerns. In this work, we implement a lightweight binary neural network (BNN) in a Cortex-M4 microcontroller (MCU) to enable the detection of four different types of heart illnesses present in a single-lead electrocardiogram (ECG) signal, in addition to proposing a blockchain-enabled HeartCare framework. The end-user can identify ailments and subsequently disseminate ECG results to medical professionals via a privacy-preserving blockchain-enabled framework. To acquire the ECG signal, a reusable fabric electrode was proposed and successfully fabricated. Finally, the BNN model is being trained utilising ECG databases of patients from the Indian continent, in addition to other state-of-the-art databases. The post-deployment validation of the proposed framework was conducted rigorously in alignment with the ACC/AHA Guidelines, resulting in an overall accuracy of 95.93% and a sensitivity of 95.90% for our BNN model.
{"title":"Blockchain-Enabled HeartCare Framework for Cardiovascular Disease Diagnosis in Devices With Constrained Resources","authors":"Bidyut Bikash Borah;Khushboo Das;Geetartha Sarma;Soumik Roy;Dhruba Kumar Bhattacharyya","doi":"10.1109/TSC.2024.3489442","DOIUrl":"10.1109/TSC.2024.3489442","url":null,"abstract":"Cardiovascular diseases (CVDs) are the primary cause of mortality worldwide. The healthcare sector in India currently shows promise for substantial changes, specifically in the utilization and importance of the Internet of Medical Things (IoMT). Edge computing is necessary to make the IoMT more scalable, portable, reliable, and responsive. Security and privacy concerns impede the development and deployment of IoMT devices. The technology of blockchain can resolve security and privacy concerns. In this work, we implement a lightweight binary neural network (BNN) in a Cortex-M4 microcontroller (MCU) to enable the detection of four different types of heart illnesses present in a single-lead electrocardiogram (ECG) signal, in addition to proposing a blockchain-enabled HeartCare framework. The end-user can identify ailments and subsequently disseminate ECG results to medical professionals via a privacy-preserving blockchain-enabled framework. To acquire the ECG signal, a reusable fabric electrode was proposed and successfully fabricated. Finally, the BNN model is being trained utilising ECG databases of patients from the Indian continent, in addition to other state-of-the-art databases. The post-deployment validation of the proposed framework was conducted rigorously in alignment with the ACC/AHA Guidelines, resulting in an overall accuracy of 95.93% and a sensitivity of 95.90% for our BNN model.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3185-3198"},"PeriodicalIF":5.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Microservices improve the scalability and flexibility of monolithic architectures to accommodate the evolution of software systems, but the complexity and dynamics of microservices challenge system reliability. Ensuring microservice quality requires efficient failure diagnosis, including detection and triage. Failure detection involves identifying anomalous behavior within the system, while triage entails classifying the failure type and directing it to the engineering team for resolution. Unfortunately, current approaches reliant on single-modal monitoring data, such as metrics, logs, or traces, cannot capture all failures and neglect interconnections among multimodal data, leading to erroneous diagnoses. Recent multimodal data fusion studies struggle to achieve deep integration, limiting diagnostic accuracy due to insufficiently captured interdependencies. Therefore, we propose UniDiag , which leverages temporal knowledge graphs to fuse multimodal data for effective failure diagnosis. UniDiag applies a simple yet effective stream-based anomaly detection method to reduce computational cost and a novel microservice-oriented graph embedding method to represent the state of systems comprehensively. To assess the performance of UniDiag , we conduct extensive evaluation experiments using datasets from two benchmark microservice systems, demonstrating its superiority over existing methods and affirming the efficacy of multimodal data fusion. Additionally, we have publicly made the code and data available to facilitate further research.
{"title":"No More Data Silos: Unified Microservice Failure Diagnosis With Temporal Knowledge Graph","authors":"Shenglin Zhang;Yongxin Zhao;Sibo Xia;Shirui Wei;Yongqian Sun;Chenyu Zhao;Shiyu Ma;Junhua Kuang;Bolin Zhu;Lemeng Pan;Yicheng Guo;Dan Pei","doi":"10.1109/TSC.2024.3489444","DOIUrl":"10.1109/TSC.2024.3489444","url":null,"abstract":"Microservices improve the scalability and flexibility of monolithic architectures to accommodate the evolution of software systems, but the complexity and dynamics of microservices challenge system reliability. Ensuring microservice quality requires efficient failure diagnosis, including detection and triage. Failure detection involves identifying anomalous behavior within the system, while triage entails classifying the failure type and directing it to the engineering team for resolution. Unfortunately, current approaches reliant on single-modal monitoring data, such as metrics, logs, or traces, cannot capture all failures and neglect interconnections among multimodal data, leading to erroneous diagnoses. Recent multimodal data fusion studies struggle to achieve deep integration, limiting diagnostic accuracy due to insufficiently captured interdependencies. Therefore, we propose \u0000<italic>UniDiag</i>\u0000, which leverages temporal knowledge graphs to fuse multimodal data for effective failure diagnosis. \u0000<italic>UniDiag</i>\u0000 applies a simple yet effective stream-based anomaly detection method to reduce computational cost and a novel microservice-oriented graph embedding method to represent the state of systems comprehensively. To assess the performance of \u0000<italic>UniDiag</i>\u0000, we conduct extensive evaluation experiments using datasets from two benchmark microservice systems, demonstrating its superiority over existing methods and affirming the efficacy of multimodal data fusion. Additionally, we have publicly made the code and data available to facilitate further research.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"4013-4026"},"PeriodicalIF":5.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1109/TSC.2024.3489432
Xiangqian Kong;Lanxiang Chen;Yizhao Zhu;Yi Mu
Public-key Encryption with Keyword Search (PEKS) enables secure keyword searches within encrypted data. At the same time, Public-key Authenticated Encryption with Keyword Search (PAEKS) enhances security by permitting authorized users to search specific keyword sets, protecting against Internal Keyword Guessing Attacks (IKGA). However, to the best of our knowledge, existing PEKS and PAEKS schemes typically require to generate a distinct set of keyword ciphertext for each data user, leading to storage, computation, and communication costs and the lack of support for multiple-keyword search. In this article, we introduce a novel, efficient public-key searchable encryption scheme from the private set intersection (PSI) with scalable proxy servers, using a PSI protocol with multiple proxy server settings, which achieves sub-linear complexity. Our scheme is secure against IKGA and supports multiple keyword searches and sharing one encrypted keyword set by multiple users. We introduce an efficient system model with scalable proxy servers, significantly reducing computational overhead through a divide-and-conquer approach. Our proposed scheme supports multiple data users, and multiple keyword searches, utilizing a single set of keyword ciphertext for multiple data users. We formally define a security model and present a comprehensive security proof to demonstrate that our scheme maintains ciphertext-indistinguishability and trapdoor-indistinguishability.
{"title":"Efficient Public-Key Searchable Encryption Scheme From PSI With Scalable Proxy Servers","authors":"Xiangqian Kong;Lanxiang Chen;Yizhao Zhu;Yi Mu","doi":"10.1109/TSC.2024.3489432","DOIUrl":"10.1109/TSC.2024.3489432","url":null,"abstract":"Public-key Encryption with Keyword Search (PEKS) enables secure keyword searches within encrypted data. At the same time, Public-key Authenticated Encryption with Keyword Search (PAEKS) enhances security by permitting authorized users to search specific keyword sets, protecting against Internal Keyword Guessing Attacks (IKGA). However, to the best of our knowledge, existing PEKS and PAEKS schemes typically require to generate a distinct set of keyword ciphertext for each data user, leading to storage, computation, and communication costs and the lack of support for multiple-keyword search. In this article, we introduce a novel, efficient public-key searchable encryption scheme from the private set intersection (PSI) with scalable proxy servers, using a PSI protocol with multiple proxy server settings, which achieves sub-linear complexity. Our scheme is secure against IKGA and supports multiple keyword searches and sharing one encrypted keyword set by multiple users. We introduce an efficient system model with scalable proxy servers, significantly reducing computational overhead through a divide-and-conquer approach. Our proposed scheme supports multiple data users, and multiple keyword searches, utilizing a single set of keyword ciphertext for multiple data users. We formally define a security model and present a comprehensive security proof to demonstrate that our scheme maintains ciphertext-indistinguishability and trapdoor-indistinguishability.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3527-3540"},"PeriodicalIF":5.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1109/tsc.2024.3489443
Yaning Yang, Xiao Du, Yutong Ye, Jiepin Ding, Ting Wang, Mingsong Chen, Keqin Li
{"title":"Multi-objective Deep Reinforcement Learning for Function Offloading in Serverless Edge Computing","authors":"Yaning Yang, Xiao Du, Yutong Ye, Jiepin Ding, Ting Wang, Mingsong Chen, Keqin Li","doi":"10.1109/tsc.2024.3489443","DOIUrl":"https://doi.org/10.1109/tsc.2024.3489443","url":null,"abstract":"","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"87 1","pages":""},"PeriodicalIF":8.1,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1109/TSC.2024.3489439
Dabao Wang;Bang Wu;Xingliang Yuan;Lei Wu;Yajin Zhou;Helei Cui
The prosperity of Decentralized Finance (DeFi) unveils underlying risks, with reported losses surpassing 3.2 billion USD between 2018 and 2022 due to vulnerabilities in Decentralized Applications (DApps). One significant threat is the Price Manipulation Attack (PMA) that alters asset prices during transaction execution. As a result, PMA accounts for over 50 million USD in losses. To address the urgent need for efficient PMA detection, this article introduces a novel detection service, DeFiGuard , using Graph Neural Networks (GNNs). In this article, we propose cash flow graphs with four distinct features, which capture the trading behaviors from transactions. Moreover, DeFiGuard integrates transaction parsing, graph construction, model training, and PMA detection. Evaluations on the collected transactions demonstrate that DeFiGuard with GNN models outperforms the baseline MLP model and classical classification models in Accuracy, TPR, FPR, and AUC-ROC. The results of ablation studies suggest that the combination of the four proposed node features enhances DeFiGuard ’s efficacy. Moreover, DeFiGuard classifies transactions within 0.892 to 5.317 seconds, which provides sufficient time for the victims (DApps and users) to take action to rescue their vulnerable funds. In conclusion, this research offers a significant step towards safeguarding the DeFi landscape from PMAs using GNNs.
{"title":"DeFiGuard: A Price Manipulation Detection Service in DeFi Using Graph Neural Networks","authors":"Dabao Wang;Bang Wu;Xingliang Yuan;Lei Wu;Yajin Zhou;Helei Cui","doi":"10.1109/TSC.2024.3489439","DOIUrl":"10.1109/TSC.2024.3489439","url":null,"abstract":"The prosperity of Decentralized Finance (DeFi) unveils underlying risks, with reported losses surpassing 3.2 billion USD between 2018 and 2022 due to vulnerabilities in Decentralized Applications (DApps). One significant threat is the Price Manipulation Attack (PMA) that alters asset prices during transaction execution. As a result, PMA accounts for over 50 million USD in losses. To address the urgent need for efficient PMA detection, this article introduces a novel detection service, \u0000<italic>DeFiGuard</i>\u0000, using Graph Neural Networks (GNNs). In this article, we propose cash flow graphs with four distinct features, which capture the trading behaviors from transactions. Moreover, \u0000<italic>DeFiGuard</i>\u0000 integrates transaction parsing, graph construction, model training, and PMA detection. Evaluations on the collected transactions demonstrate that \u0000<italic>DeFiGuard</i>\u0000 with GNN models outperforms the baseline MLP model and classical classification models in Accuracy, TPR, FPR, and AUC-ROC. The results of ablation studies suggest that the combination of the four proposed node features enhances \u0000<italic>DeFiGuard</i>\u0000 ’s efficacy. Moreover, \u0000<italic>DeFiGuard</i>\u0000 classifies transactions within 0.892 to 5.317 seconds, which provides sufficient time for the victims (DApps and users) to take action to rescue their vulnerable funds. In conclusion, this research offers a significant step towards safeguarding the DeFi landscape from PMAs using GNNs.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3345-3358"},"PeriodicalIF":5.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1109/TSC.2024.3489417
Mingdong Tang;Jiajin Mai;Fenfang Xie;Zibin Zheng
Mashup technology enables developers to create new applications more readily by combining existing services. As its popularity grows, research on service recommendation for mashup creation has gained increasing attention. Existing recommendation methods have the following limitations: either they are susceptible to data sparsity problems, or they exhibit over-smoothing when aggregating high-order neighbors, resulting in similar and non-specific node feature representations, or they only focus on bipartite graphs and neglect the rich heterogeneous information in the mashup-service ecosystem. To address these issues, we propose a service recommendation method for mashup creation based on l ight h eterogeneous hyper g raph c ontrastive l earning (LHGCL). This method first constructs a heterogeneous hypergraph by combining mashup information, service information, the mashup-service interaction data, and their related attribute information. Then, it designs a light hypergraph neural network to capture the high-order relationships between mashups and services. Next, it applies contrastive learning to enhance the representations of mashups and services. Finally, it utilizes the enhanced feature vectors of mashups and services to predict mashup preferences for services. Comprehensive experiments conducted on the real-world ProgrammableWeb dataset demonstrate the superiority of the proposed method and the effectiveness of its key modules.
{"title":"Light Heterogeneous Hypergraph Contrastive Learning Based Service Recommendation for Mashup Creation","authors":"Mingdong Tang;Jiajin Mai;Fenfang Xie;Zibin Zheng","doi":"10.1109/TSC.2024.3489417","DOIUrl":"10.1109/TSC.2024.3489417","url":null,"abstract":"Mashup technology enables developers to create new applications more readily by combining existing services. As its popularity grows, research on service recommendation for mashup creation has gained increasing attention. Existing recommendation methods have the following limitations: either they are susceptible to data sparsity problems, or they exhibit over-smoothing when aggregating high-order neighbors, resulting in similar and non-specific node feature representations, or they only focus on bipartite graphs and neglect the rich heterogeneous information in the mashup-service ecosystem. To address these issues, we propose a service recommendation method for mashup creation based on \u0000<underline>l</u>\u0000ight \u0000<underline>h</u>\u0000eterogeneous hyper\u0000<underline>g</u>\u0000raph \u0000<underline>c</u>\u0000ontrastive \u0000<underline>l</u>\u0000earning (LHGCL). This method first constructs a heterogeneous hypergraph by combining mashup information, service information, the mashup-service interaction data, and their related attribute information. Then, it designs a light hypergraph neural network to capture the high-order relationships between mashups and services. Next, it applies contrastive learning to enhance the representations of mashups and services. Finally, it utilizes the enhanced feature vectors of mashups and services to predict mashup preferences for services. Comprehensive experiments conducted on the real-world ProgrammableWeb dataset demonstrate the superiority of the proposed method and the effectiveness of its key modules.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"17 6","pages":"3844-3856"},"PeriodicalIF":5.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1109/tsc.2024.3486226
Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani, Paolo G. Panero
{"title":"Continuous Management of Machine Learning-Based Application Behavior","authors":"Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani, Paolo G. Panero","doi":"10.1109/tsc.2024.3486226","DOIUrl":"https://doi.org/10.1109/tsc.2024.3486226","url":null,"abstract":"","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 1","pages":""},"PeriodicalIF":8.1,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142536808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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：