Guangyuan Piao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Guangyuan Piao has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
John G. Breslin
IDA Business Park
10 shared publications- John G. Breslin
University of Galway
7 shared publications - Changbo Deng
Tencent Security Big Data Lab
2 shared publications - Junjie Tao
Ministry of Education Key Laboratory of Intelligent Networks and Network Security, Xian Jiaotong University, Xian, Shaanxi, China
2 shared publications - Ming Fan
Xi’an Jiaotong University
2 shared publications Patrick K. Nicholson
Autonomous Software Systems Research, Nokia Bell Labs, Dublin 15, Ireland
2 shared publications
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4476-4486
Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4476-4486
Open AccessEnhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning
- Open Access
Rényi Divergence Deep Mutual Learning
This paper revisits Deep Mutual Learning (DML), a simple yet effective computing paradigm. We propose using R\'{e}nyi divergence instead of the KL divergence, which is more flexible and tunable, to improve vanilla DML. This modification is able to consistently improve performance over vanilla DML with limited additional complexity. The convergence properties of the proposed paradigm are analyzed theoretically, and Stochastic Gradient Descent with a constant learning rate is shown to converge with $\mathcal{O}(1)$-bias in the worst case scenario for nonconvex optimization tasks. That is, learning will reach nearby local optima but continue searching within a bounded scope, which may help mitigate overfitting. Finally, our extensive empirical results demonstrate the advantage of combining DML and R\'{e}nyi divergence, leading to further improvement in model generalization.
Open AccessRényi Divergence Deep Mutual Learning
This paper revisits Deep Mutual Learning (DML), a simple yet effective computing paradigm. We propose using R\'{e}nyi divergence instead of the KL divergence, which is more flexible and tunable, to improve vanilla DML. This modification is able to consistently improve performance over vanilla DML with limited additional complexity. The convergence properties of the proposed paradigm are analyzed theoretically, and Stochastic Gradient Descent with a constant learning rate is shown to converge with $\mathcal{O}(1)$-bias in the worst case scenario for nonconvex optimization tasks. That is, learning will reach nearby local optima but continue searching within a bounded scope, which may help mitigate overfitting. Finally, our extensive empirical results demonstrate the advantage of combining DML and R\'{e}nyi divergence, leading to further improvement in model generalization.
- 30 September 2021
- Published by Springer Nature
- p. 39-55
Learning to Predict the Departure Dynamics of Wikidata Editors
- 30 September 2021
- Published by Springer Nature
- p. 39-55
Learning to Predict the Departure Dynamics of Wikidata Editors
- 24 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 18 (3) , 3567-3582
Data-Driven Energy Conservation in Cellular Networks: A Systems Approach
The energy consumption of mobile networks is already substantial nowadays, and only expected to further increase with the roll-out of 5G. Base stations are the key elements in this context: reducing their energy consumption is of paramount importance for network operators, not only to lower operating costs, but also to meet sustainable development goals. Today's base stations are typically over-provisioned, i.e., they comprise multiple cells to meet the peak load in a region. Therefore, substantial energy savings are possible by switching off cells that are under-utilized. This article proposes a data-driven approach to determine the time periods when a cell can be switched off. Forecasting is used to accurately predict network utilization and automatically find the time intervals to reliably switch off a cell. We carefully analyze the requirements of the system as a whole, from data collection to forecasting methods, to enable effective energy savings in practice. Considering several real-world traces from LTE networks, we show that an average of 10.24% energy savings is possible. We explore the trade-offs between energy savings and overhead in switching off cells, and provide insights into the choice of methods accordingly. In particular, we show that the accuracy of forecasting is not the most important factor in achieving energy savings; instead, the prediction (uncertainty) interval plays a key role in being able to achieve energy savings with less impact on end-users. Finally, we propose a model to generate utilization traces that match the distribution of real-world traces obtained from cellular networks.
- 24 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 18 (3) , 3567-3582
Data-Driven Energy Conservation in Cellular Networks: A Systems Approach
The energy consumption of mobile networks is already substantial nowadays, and only expected to further increase with the roll-out of 5G. Base stations are the key elements in this context: reducing their energy consumption is of paramount importance for network operators, not only to lower operating costs, but also to meet sustainable development goals. Today's base stations are typically over-provisioned, i.e., they comprise multiple cells to meet the peak load in a region. Therefore, substantial energy savings are possible by switching off cells that are under-utilized. This article proposes a data-driven approach to determine the time periods when a cell can be switched off. Forecasting is used to accurately predict network utilization and automatically find the time intervals to reliably switch off a cell. We carefully analyze the requirements of the system as a whole, from data collection to forecasting methods, to enable effective energy savings in practice. Considering several real-world traces from LTE networks, we show that an average of 10.24% energy savings is possible. We explore the trade-offs between energy savings and overhead in switching off cells, and provide insights into the choice of methods accordingly. In particular, we show that the accuracy of forecasting is not the most important factor in achieving energy savings; instead, the prediction (uncertainty) interval plays a key role in being able to achieve energy savings with less impact on end-users. Finally, we propose a model to generate utilization traces that match the distribution of real-world traces obtained from cellular networks.
- 3 May 2021
- Published by Springer Nature
- p. 79-87
Scholarly Text Classification with Sentence BERT and Entity Embeddings
- 3 May 2021
- Published by Springer Nature
- p. 79-87
Scholarly Text Classification with Sentence BERT and Entity Embeddings
- Open Access
Partially Observable Markov Decision Process Modelling for Assessing Hierarchies
Hierarchical clustering has been shown to be valuable in many scenarios. Despite its usefulness to many situations, there is no agreed methodology on how to properly evaluate the hierarchies produced from different techniques, particularly in the case where ground-truth labels are unavailable. This motivates us to propose a framework for assessing the quality of hierarchical clustering allocations which covers the case of no ground-truth information. This measurement is useful, e.g., to assess the hierarchical structures used by online retailer websites to display their product catalogues. Our framework is one of the few attempts for the hierarchy evaluation from a decision-theoretic perspective. We model the process as a bot searching stochastically for items in the hierarchy and establish a measure representing the degree to which the hierarchy supports this search. We employ Partially Observable Markov Decision Processes (POMDP) to model the uncertainty, the decision making, and the cognitive return for searchers in such a scenario.
Open AccessPartially Observable Markov Decision Process Modelling for Assessing Hierarchies
Hierarchical clustering has been shown to be valuable in many scenarios. Despite its usefulness to many situations, there is no agreed methodology on how to properly evaluate the hierarchies produced from different techniques, particularly in the case where ground-truth labels are unavailable. This motivates us to propose a framework for assessing the quality of hierarchical clustering allocations which covers the case of no ground-truth information. This measurement is useful, e.g., to assess the hierarchical structures used by online retailer websites to display their product catalogues. Our framework is one of the few attempts for the hierarchy evaluation from a decision-theoretic perspective. We model the process as a bot searching stochastically for items in the hierarchy and establish a measure representing the degree to which the hierarchy supports this search. We employ Partially Observable Markov Decision Processes (POMDP) to model the uncertainty, the decision making, and the cognitive return for searchers in such a scenario.
- Open Access
- 15 April 2020
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Env2Vec
The adoption of fast-paced practices for developing virtual network functions (VNFs) allows for continuous software delivery and creates a market advantage for network operators. This adoption, however, is problematic for testing engineers that need to assure, in shorter development cycles, certain quality of highly-configurable product releases running on heterogeneous clouds. Machine learning (ML) can accelerate testing workflows by detecting performance issues in new software builds. However, the overhead of maintaining several models for all combinations of build types, network configurations, and other stack parameters, can quickly become prohibitive and make the application of ML infeasible. We propose Env2Vec, a deep learning architecture that combines contextual features with historical resource usage, and characterizes the various stack parameters that influence the test execution within an embedding space, which allows it to generalize model predictions to previously unseen environments. We integrate a single ML model in the testing workflow to automatically debug errors and pinpoint performance bottlenecks. Results obtained with real testing data show an accuracy between 86.2%-100%, while reducing the false alarm rate by 20.9%-38.1% when reporting performance issues compared to state-of-the-art approaches.
- 15 April 2020
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessEnv2Vec
The adoption of fast-paced practices for developing virtual network functions (VNFs) allows for continuous software delivery and creates a market advantage for network operators. This adoption, however, is problematic for testing engineers that need to assure, in shorter development cycles, certain quality of highly-configurable product releases running on heterogeneous clouds. Machine learning (ML) can accelerate testing workflows by detecting performance issues in new software builds. However, the overhead of maintaining several models for all combinations of build types, network configurations, and other stack parameters, can quickly become prohibitive and make the application of ML infeasible. We propose Env2Vec, a deep learning architecture that combines contextual features with historical resource usage, and characterizes the various stack parameters that influence the test execution within an embedding space, which allows it to generalize model predictions to previously unseen environments. We integrate a single ML model in the testing workflow to automatically debug errors and pinpoint performance bottlenecks. Results obtained with real testing data show an accuracy between 86.2%-100%, while reducing the false alarm rate by 20.9%-38.1% when reporting performance issues compared to state-of-the-art approaches.
- 17 October 2018
- Published by Springer Nature
- p. 129-139
Domain-Aware Sentiment Classification with GRUs and CNNs
- 17 October 2018
- Published by Springer Nature
- p. 129-139
Domain-Aware Sentiment Classification with GRUs and CNNs
- 18 August 2018
- Published by Springer Nature in User Modeling and User-Adapted Interaction
- Vol. 28 (3) , 277-329
Inferring user interests in microblogging social networks: a survey
- 18 August 2018
- Published by Springer Nature in User Modeling and User-Adapted Interaction
- Vol. 28 (3) , 277-329
Inferring user interests in microblogging social networks: a survey