Pei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pei Li has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Jianxun Liu
Key Lab. for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China
5 shared publications - Dong Zhou
Guangdong University of Foreign Studies
4 shared publications - Hui Wang
College of Systems Engineering Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology
3 shared publications - Hui Wang
College of Information Systems and Management, National University of Defense Technology, Changsha, Hunan 410073, China
3 shared publications - Xin Zhang
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
3 shared publications - Yang Gao
School of Computer Science and Engineering, Hunan University of Science and Technology, 411201, China
3 shared publications
Latest Publications
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (1) , 727-738
TCL: Trustworthy Contrastive Learning for Web API Recommendation via Exploring Textual and Structural Semantics
With the development of service-oriented computing, software developers increasingly rely on diverse Web application programming interfaces (APIs, also known as Web services) from unmanned Web API markets. This trend aims to expedite the development of feature-rich Mashup applications while simultaneously reducing time and costs. However, the growing abundance of Web APIs presents a challenge in service discovery. Consequently, Web API recommendation is proposed as a vital strategy for facilitating service discovery. Nonetheless, existing approaches to Web API recommendation suffer from limitations in effectively extracting rich semantics from description documents and service networks, leading to suboptimal recommendation performance. To address this issue, this article proposes trustworthy contrastive learning (TCL) for Web API recommendation via exploring textual and structural semantics, named TCL. TCL takes the trustworthiness of both the textual and structural representations into account to differentiate the loss of contrastive learning so that both textual and structural representation learning can be mutually improved. Empirical evaluations conducted on a real-world dataset crawled from ProgrammableWeb.com demonstrate the effectiveness of the proposed approach, showcasing its superiority over baseline methods.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (1) , 727-738
TCL: Trustworthy Contrastive Learning for Web API Recommendation via Exploring Textual and Structural Semantics
With the development of service-oriented computing, software developers increasingly rely on diverse Web application programming interfaces (APIs, also known as Web services) from unmanned Web API markets. This trend aims to expedite the development of feature-rich Mashup applications while simultaneously reducing time and costs. However, the growing abundance of Web APIs presents a challenge in service discovery. Consequently, Web API recommendation is proposed as a vital strategy for facilitating service discovery. Nonetheless, existing approaches to Web API recommendation suffer from limitations in effectively extracting rich semantics from description documents and service networks, leading to suboptimal recommendation performance. To address this issue, this article proposes trustworthy contrastive learning (TCL) for Web API recommendation via exploring textual and structural semantics, named TCL. TCL takes the trustworthiness of both the textual and structural representations into account to differentiate the loss of contrastive learning so that both textual and structural representation learning can be mutually improved. Empirical evaluations conducted on a real-world dataset crawled from ProgrammableWeb.com demonstrate the effectiveness of the proposed approach, showcasing its superiority over baseline methods.
- 8 July 2022
- Published by Springer Nature
- p. 327-339
Minimizing Immune Costs in Social Networks Through Reinforcement Learning
- 8 July 2022
- Published by Springer Nature
- p. 327-339
Minimizing Immune Costs in Social Networks Through Reinforcement Learning
- Open Access
6G-enabled Edge AI for Metaverse: Challenges, Methods, and Future Research Directions
6G-enabled edge intelligence opens up a new era of Internet of Everything and makes it possible to interconnect people-devices-cloud anytime, anywhere. More and more next-generation wireless network smart service applications are changing our way of life and improving our quality of life. As the hottest new form of next-generation Internet applications, Metaverse is striving to connect billions of users and create a shared world where virtual and reality merge. However, limited by resources, computing power, and sensory devices, Metaverse is still far from realizing its full vision of immersion, materialization, and interoperability. To this end, this survey aims to realize this vision through the organic integration of 6G-enabled edge AI and Metaverse. Specifically, we first introduce three new types of edge-Metaverse architectures that use 6G-enabled edge AI to solve resource and computing constraints in Metaverse. Then we summarize technical challenges that these architectures face in Metaverse and the existing solutions. Furthermore, we explore how the edge-Metaverse architecture technology helps Metaverse to interact and share digital data. Finally, we discuss future research directions to realize the true vision of Metaverse with 6G-enabled edge AI.
Open Access6G-enabled Edge AI for Metaverse: Challenges, Methods, and Future Research Directions
6G-enabled edge intelligence opens up a new era of Internet of Everything and makes it possible to interconnect people-devices-cloud anytime, anywhere. More and more next-generation wireless network smart service applications are changing our way of life and improving our quality of life. As the hottest new form of next-generation Internet applications, Metaverse is striving to connect billions of users and create a shared world where virtual and reality merge. However, limited by resources, computing power, and sensory devices, Metaverse is still far from realizing its full vision of immersion, materialization, and interoperability. To this end, this survey aims to realize this vision through the organic integration of 6G-enabled edge AI and Metaverse. Specifically, we first introduce three new types of edge-Metaverse architectures that use 6G-enabled edge AI to solve resource and computing constraints in Metaverse. Then we summarize technical challenges that these architectures face in Metaverse and the existing solutions. Furthermore, we explore how the edge-Metaverse architecture technology helps Metaverse to interact and share digital data. Finally, we discuss future research directions to realize the true vision of Metaverse with 6G-enabled edge AI.
- 7 May 2021
- Published by Springer Nature
- p. 130-141
Impacts of Individuals’ Trust in Information Diffusion of the Weighted Multiplex Networks
- 7 May 2021
- Published by Springer Nature
- p. 130-141
Impacts of Individuals’ Trust in Information Diffusion of the Weighted Multiplex Networks
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Dual‐Level Attention Based on a Heterogeneous Graph Convolution Network for Aspect‐Based Sentiment Classification
With the development of 5G, the advancement of basic infrastructure has led to considerable development in related research and technology. It also promotes the development of various smart devices and social platforms. More and more people are now using smart devices to post their reviews right after something happens. In order to keep pace with this trend, we propose a method to analyze users’ sentiment by using their text data. When analyzing users’ text data, it is noted that a user’s review may contain many aspects. Traditional text classification methods used by smart devices, however, usually ignore the importance of multiple aspects of a review. Additionally, most algorithms usually ignore the network structure information between the words in a sentence and the sentence itself. To address these issues, we propose a novel dual‐level attention‐based heterogeneous graph convolutional network for aspect‐based sentiment classification which minds more context information through information propagation along with graphs. Particularly, we first propose a flexible HIN (heterogeneous information network) framework to model the user‐generated reviews. This framework can integrate various types of additional information and capture their relationships to alleviate semantic sparsity of some labeled data. This framework can also leverage the full advantage of the hidden network structure information through information propagation along with graphs. Then, we propose a dual‐level attention‐based heterogeneous graph convolutional network (DAHGCN), which includes node‐level and type‐level attentions. The attention mechanisms can analyze the importance of different adjacent nodes and the importance of different types of nodes for the current node. The experimental results on three real‐world datasets demonstrated the effectiveness and reliability of our model.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessDual‐Level Attention Based on a Heterogeneous Graph Convolution Network for Aspect‐Based Sentiment Classification
With the development of 5G, the advancement of basic infrastructure has led to considerable development in related research and technology. It also promotes the development of various smart devices and social platforms. More and more people are now using smart devices to post their reviews right after something happens. In order to keep pace with this trend, we propose a method to analyze users’ sentiment by using their text data. When analyzing users’ text data, it is noted that a user’s review may contain many aspects. Traditional text classification methods used by smart devices, however, usually ignore the importance of multiple aspects of a review. Additionally, most algorithms usually ignore the network structure information between the words in a sentence and the sentence itself. To address these issues, we propose a novel dual‐level attention‐based heterogeneous graph convolutional network for aspect‐based sentiment classification which minds more context information through information propagation along with graphs. Particularly, we first propose a flexible HIN (heterogeneous information network) framework to model the user‐generated reviews. This framework can integrate various types of additional information and capture their relationships to alleviate semantic sparsity of some labeled data. This framework can also leverage the full advantage of the hidden network structure information through information propagation along with graphs. Then, we propose a dual‐level attention‐based heterogeneous graph convolutional network (DAHGCN), which includes node‐level and type‐level attentions. The attention mechanisms can analyze the importance of different adjacent nodes and the importance of different types of nodes for the current node. The experimental results on three real‐world datasets demonstrated the effectiveness and reliability of our model.
- 17 November 2020
- Published by Springer Nature
- p. 685-692
Multitask Learning Based on Constrained Hierarchical Attention Network for Multi-aspect Sentiment Classification
- 17 November 2020
- Published by Springer Nature
- p. 685-692
Multitask Learning Based on Constrained Hierarchical Attention Network for Multi-aspect Sentiment Classification
- Open Access
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1878-1881
Discovering Band Order Dependencies
We introduce band ODs to model the semantics of attributes that are monotonically related with small variations without there being an intrinsic violation of semantics. To make band ODs relevant to real-world applications, we make them less strict to hold approximately with some exceptions. Since formulating integrity constraints manually is cumbersome, we study the problem of automatic approximate band OD discovery. We devise an algorithm that determines the optimal solution in polynomial time. We perform a thorough experimental evaluation of our techniques over real-world and synthetic datasets.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1878-1881
Open AccessDiscovering Band Order Dependencies
We introduce band ODs to model the semantics of attributes that are monotonically related with small variations without there being an intrinsic violation of semantics. To make band ODs relevant to real-world applications, we make them less strict to hold approximately with some exceptions. Since formulating integrity constraints manually is cumbersome, we study the problem of automatic approximate band OD discovery. We devise an algorithm that determines the optimal solution in polynomial time. We perform a thorough experimental evaluation of our techniques over real-world and synthetic datasets.
- Open Access
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 21943-21952
Modeling and Estimating User Influence in Social Networks
It is of importance to model and estimate the user influence in social networks, especially for advertisers who conduct viral marketing. In this paper, we are interested in the number of received messages incurred by a node generating a message, and introduce the concepts of individual influence and type influence, while type influence is got by averaging out individual influence over nodes of the same type. We propose a user behavior model and use generating function to analyze type influence (including the mean and variance) and diffusion threshold, and find these results are not accurate in finite-size networks. We then classify nodes into subtypes and redefine the network model, which achieves much more accurate results. We also propose a scalable approach to estimate individual influence, and find it can get good approximates for individual influence, subtype influence and type influence by only considering local neighbors and out-of-date information, which is useful in large-scale networks. All analysis results are verified by simulations in real-world networks. Models in this paper can be extended to consider more realistic situations, and we believe these results are of use in understanding the diffusion dynamics in social networks.
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 21943-21952
Open AccessModeling and Estimating User Influence in Social Networks
It is of importance to model and estimate the user influence in social networks, especially for advertisers who conduct viral marketing. In this paper, we are interested in the number of received messages incurred by a node generating a message, and introduce the concepts of individual influence and type influence, while type influence is got by averaging out individual influence over nodes of the same type. We propose a user behavior model and use generating function to analyze type influence (including the mean and variance) and diffusion threshold, and find these results are not accurate in finite-size networks. We then classify nodes into subtypes and redefine the network model, which achieves much more accurate results. We also propose a scalable approach to estimate individual influence, and find it can get good approximates for individual influence, subtype influence and type influence by only considering local neighbors and out-of-date information, which is useful in large-scale networks. All analysis results are verified by simulations in real-world networks. Models in this paper can be extended to consider more realistic situations, and we believe these results are of use in understanding the diffusion dynamics in social networks.
- Open Access
- 20 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 168548-168556
CE-HEAT: An Aspect-Level Sentiment Classification Approach With Collaborative Extraction Hierarchical Attention Network
Aspect-level sentiment classification is a fine-grained sentiment analysis task. It aims to predict the sentiment of a review in different aspects. Recently many works exploit the hierarchical attention network to capture the aspect-specific sentiment information. However, the prior work only attends to use the aspect terms to capture the aspect-specific sentiment information in the text. It may cause the mismatch of sentiment for the aspect-specific when the aspect words are extracted incorrectly. Since the number of aspect words is much more than that sentiment words, some uncommon aspect terms are more difficult to be extracted than uncommon sentiment terms. To solve this problem, we propose a collaborative extraction hierarchical attention network. It consists of two hierarchical attention units, i.e.. One unit extracts the sentiment features by the sentiment attention layer and uses the sentiment features to capture the specific aspect-related sentiment aspect information by the aspect attention layer. The other extracts the aspect features by the aspect attention layer and uses the aspect features to help capture the aspect-specific sentiment information by the sentiment attention layer. Moreover, we use the SemEval competition data set to verify our approach. The experiment shows that our approach achieves better performance than the methods which only use aspect features to extract sentiment feature for aspect-level sentiment classification.
- 20 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 168548-168556
Open AccessCE-HEAT: An Aspect-Level Sentiment Classification Approach With Collaborative Extraction Hierarchical Attention Network
Aspect-level sentiment classification is a fine-grained sentiment analysis task. It aims to predict the sentiment of a review in different aspects. Recently many works exploit the hierarchical attention network to capture the aspect-specific sentiment information. However, the prior work only attends to use the aspect terms to capture the aspect-specific sentiment information in the text. It may cause the mismatch of sentiment for the aspect-specific when the aspect words are extracted incorrectly. Since the number of aspect words is much more than that sentiment words, some uncommon aspect terms are more difficult to be extracted than uncommon sentiment terms. To solve this problem, we propose a collaborative extraction hierarchical attention network. It consists of two hierarchical attention units, i.e.. One unit extracts the sentiment features by the sentiment attention layer and uses the sentiment features to capture the specific aspect-related sentiment aspect information by the aspect attention layer. The other extracts the aspect features by the aspect attention layer and uses the aspect features to help capture the aspect-specific sentiment information by the sentiment attention layer. Moreover, we use the SemEval competition data set to verify our approach. The experiment shows that our approach achieves better performance than the methods which only use aspect features to extract sentiment feature for aspect-level sentiment classification.