Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Yujing Wang et al.
Summary: In this paper, a novel and generic evolving attention mechanism is proposed, which models the evolution of inter-token relationships through a chain of residual convolutional modules. Experimental results show that the networks equipped with this mechanism achieve superior performance in various applications.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Meng-Hao Guo et al.
Summary: Attention mechanisms, especially self-attention, are crucial for deep feature representation in visual tasks. This article proposes a novel attention mechanism called external attention, which uses shared memories to capture correlations between samples and has lower computational and memory costs compared to self-attention. Experimental results demonstrate that our method achieves comparable or superior results in various visual tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yanping Chen et al.
Summary: This paper proposes a temporal regularized tensor factorization method based on hybrid CF for QoS prediction of mobile services, representing the overall structure of QoS data by constructing a user-service-time tensor model and introducing a temporal regular term for relationship mining to predict missing values.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Qingren Wang et al.
Summary: This paper proposes a location-based deep factorization machine model (LDFM) to address the challenges of sparse data and performance fluctuation in service recommendation. LDFM extends the dataset, extracts potential features, and weights extracted features using location information and information entropy, thus improving the accuracy and robustness of QoS predictions.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Armielle Noulapeu Ngaffo et al.
Summary: The rise of high-quality cloud services has made service recommendation crucial. QoS prediction is essential for users to choose high-quality cloud services. To address the challenges of data sparsity, a sustainable service recommendation method is proposed to predict relevant services for end-users accurately.
APPLIED INTELLIGENCE
(2022)
Review
Computer Science, Theory & Methods
Yuanyi Chen et al.
Summary: This study proposes a context-aware feature interaction modeling approach for QoS prediction of IoT services, which captures both low-order and high-order feature interactions through a multi-phase learning and fusion process. Experimental results show that the proposed method consistently outperforms state-of-the-art baselines in various evaluation metrics.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Theory & Methods
Jiahui Li et al.
Summary: With the widespread deployment of cloud computing and service-oriented systems, collaborative QoS prediction has become increasingly demanded. Existing methods have made progress in modeling users and services as well as utilizing service invocation contexts, but they overlook the impact of underlying network topology and interactions between Autonomous Systems on the completion of service requests/responses. To address this, we propose a topology-aware neural (TAN) model that comprehensively captures the invocation context for accurate QoS prediction.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Youhao Xia et al.
Summary: In this article, a JDNMFL framework is proposed for QoS prediction, which uses joint deep networks to extract and learn deep features of users/services and improve prediction accuracy. Experimental results demonstrate the effectiveness of this method in QoS prediction with sparse data.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Zhu Yuan et al.
Summary: This paper proposes a fine-grained framework called CSEA for energy-aware cloud storage system based on climatic seasons. By mining data features and using the K-means clustering algorithm, CSEA achieves fine-grained data distribution, thereby reducing energy consumption and operating cost.
Article
Computer Science, Information Systems
Xiaoke Zhu et al.
Summary: The study introduces a novel approach for QoS prediction in Web service recommendation, combining the SPP strategy and LLMF algorithm to protect user privacy and improve prediction accuracy.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Article
Computer Science, Information Systems
Hao Wu et al.
Summary: The proposed deep neural model (DNM) effectively integrates contextual features for multi-attributes QoS prediction, achieving superior accuracy compared to state-of-the-art techniques. The model demonstrates robustness and extensibility in exploiting heterogeneous contextual features.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Article
Computer Science, Information Systems
Yuyu Yin et al.
Summary: With the rapid development of cyber-physical systems, constructing high-quality services has become essential. A new two-stage framework called AgQ is proposed to predict QoS values by using a data augmentation strategy.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Zhenhua Chang et al.
Summary: With the development of the Internet, the recommendation based on Quality of Service (QoS) has become increasingly important in dealing with web services. The research proposes a Graph-based Matrix Factorization approach (GMF) for QoS prediction, which consolidates multi-source information and uses a Gaussian Mixture Model (GMM) to combine local and global information for accurate predictions. Extensive experimental analysis on a publicly available dataset demonstrates the accuracy and practicality of the proposed method.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jianlong Xu et al.
Summary: The study introduces a novel QoS prediction model called neural fusion matrix factorisation, which combines neural networks and matrix factorisation for non-linear collaborative filtering. Context bias is considered and multi-task learning is used to reduce prediction error and enhance predicted performance. Extensive experiments on a large-scale real-world QoS dataset validate the effectiveness of the proposed method.
CONNECTION SCIENCE
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiangyu Zhaok et al.
Summary: Research has shown that different embedding sizes are highly desired for different users/items according to their frequency, but manually selecting embedding sizes can be challenging. Therefore, this paper proposes an AutoML framework that can automatically select different embedding dimensions based on frequency.
2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
(2021)
Proceedings Paper
Computer Science, Theory & Methods
A. A. Ginart et al.
Summary: Mixed dimension embeddings are an embedding layer architecture that adjusts the dimension of embedding vectors based on query frequency, reducing memory usage while maintaining or improving machine learning performance. Empirically, they have been shown to improve accuracy by 0.1% with half as many parameters or maintain accuracy using 16x fewer parameters on the Criteo Kaggle dataset, while also training over 2x faster on a GPU.
2021 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT)
(2021)
Article
Computer Science, Interdisciplinary Applications
Mohammed Ismail Smahi et al.
Summary: The study introduces a deep-learning-based approach for QoS prediction by combining autoencoder and clustering techniques to address issues of data sparsity and cold-start.
SERVICE ORIENTED COMPUTING AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Yatao Yang et al.
Summary: With the prevalence of web services, selecting the optimal service among similar candidates relies on the Quality of Service (QoS). To enhance prediction accuracy of QoS values, a novel method based on factorization machine has been proposed, leveraging both user and service information for prediction.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Proceedings Paper
Computer Science, Information Systems
Haochen Liu et al.
PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20)
(2020)
Article
Computer Science, Theory & Methods
Qimin Zhou et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Weiping Song et al.
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19)
(2019)
Article
Computer Science, Theory & Methods
Hao Wu et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2018)
Article
Computer Science, Software Engineering
Mingdong Tang et al.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2015)
Article
Computer Science, Information Systems
Zibin Zheng et al.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2014)
Article
Computer Science, Information Systems
Zibin Zheng et al.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2013)
Article
Computer Science, Artificial Intelligence
Steffen Rendle
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2012)
Article
Computer Science, Information Systems
Zibin Zheng et al.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2011)
