Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2024
An ensemble dual model assisted MOEA/D for tackling medium scale expensive multiobjective optimization
Information Sciences: an International Journal (ISCI), Volume 679, Issue Chttps://doi.org/10.1016/j.ins.2024.121079AbstractMany surrogate-assisted evolutionary algorithms (SAEAs) have been developed to address expensive multi-objective optimization problems (EMOPs). However, existing research primarily focuses on low-dimensional EMOPs. In this article, we propose an ...
- ArticleAugust 2024
Generic and Scalable Detection of Risky Transactions Using Density Flows: Applications to Financial Networks
AbstractAlgorithms based on dense subgraphs have been proven to be highly effective in detecting financial risks, but their widespread use has been hampered by well-design density metrics and high-quality solution of densest subgraph problems. Considering ...
- research-articleJune 2024
Forecasting resource usage pattern changes in clouds via contrast graph-evolution learning
Future Generation Computer Systems (FGCS), Volume 154, Issue CPages 373–383https://doi.org/10.1016/j.future.2024.01.013AbstractThe increasing large-scale workload trace collected by datacenter monitors has provided great potential for workload prediction. However, resource usage pattern changes of workloads often exist, which are usually caused by user demand changes, ...
Highlights- We pioneer using shapelets for measuring long-term workload resource usage patterns.
- We propose a novel multi-view contrast graph-evolution learning algorithm.
- We design a GNN-based TCN encoder to realize the long-term workload ...
- research-articleJanuary 2024
EvoGWP: Predicting Long-Term Changes in Cloud Workloads Using Deep Graph-Evolution Learning
IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 35, Issue 3Pages 499–516https://doi.org/10.1109/TPDS.2024.3357715Workload prediction plays a crucial role in resource management of large scale cloud datacenters. Although quite a number of methods/algorithms have been proposed, long-term changes have not been explicitly identified and considered. Due to shifty user ...
- ArticleMarch 2024
DFECTS: A Deep Fuzzy Ensemble Clusterer for Time Series
Algorithms and Architectures for Parallel ProcessingPages 61–80https://doi.org/10.1007/978-981-97-0834-5_5AbstractTime series clustering plays an important role in various fields such as anomaly detection and resource scheduling. With the increase of complexity and scale of time series datasets, many deep-learning-based time series clustering methods have ...
-
- ArticleMay 2024
HoME: Homogeneity-Mining-Based Embedding Towards Detecting Illicit Transactions on Bitcoin
AbstractCryptocurrencies have brought booming economic innovations in recent years, but they have also given rise to many intractable problems related to financial crimes, urgently requiring for some effective countermeasures. Transaction network analysis ...
- research-articleMay 2023
MRLCC: an adaptive cloud task scheduling method based on meta reinforcement learning
Journal of Cloud Computing: Advances, Systems and Applications (JOCCASA), Volume 12, Issue 1https://doi.org/10.1186/s13677-023-00440-8AbstractTask scheduling is a complex problem in cloud computing, and attracts many researchers’ interests. Recently, many deep reinforcement learning (DRL)-based methods have been proposed to learn the scheduling policy through interacting with the ...
- ArticleFebruary 2023
Performer: A Resource Demand Forecasting Method for Data Centers
AbstractPredicting the resource demands of online tasks plays an important role in data centers, which can help cloud providers to better allocate resources and to schedule tasks. To cope with the huge number of workloads in a data center, workloads are ...
- research-articleNovember 2022
RTGA: Robust ternary gradients aggregation for federated learning
Information Sciences: an International Journal (ISCI), Volume 616, Issue CPages 427–443https://doi.org/10.1016/j.ins.2022.10.113AbstractFederated learning is a privacy-preserving machine learning paradigm that can train a model with decentralized data. Classical federated learning systems are vulnerable to attacks from malicious clients. Although a number of efforts ...
- research-articleNovember 2022
Efficient DNN training based on backpropagation parallelization
AbstractPipeline parallelism is an efficient way to speed up the training of deep neural networks (DNNs) by partitioning the model and pipelining the training process across a cluster of workers in distributed systems. In this paper, we propose a new ...
- research-articleOctober 2022
An Approximation Algorithm for the h-Hop Independently Submodular Maximization Problem and Its Applications
- Wenzheng Xu,
- Hongbin Xie,
- Chenxi Wang,
- Weifa Liang,
- Xiaohua Jia,
- Zichuan Xu,
- Pan Zhou,
- Weigang Wu,
- Xiang Chen
IEEE/ACM Transactions on Networking (TON), Volume 31, Issue 3Pages 1216–1229https://doi.org/10.1109/TNET.2022.3210825This study is motivated by the maximum connected coverage problem (MCCP), which is to deploy a connected UAV network with given <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> UAVs in the top of a disaster area such that the ...
- research-articleMay 2022
Maximizing h-hop Independently Submodular Functions Under Connectivity Constraint
IEEE INFOCOM 2022 - IEEE Conference on Computer CommunicationsPages 1099–1108https://doi.org/10.1109/INFOCOM48880.2022.9796957This study is motivated by the maximum connected coverage problem (MCCP), which is to deploy a connected UAV network with given K UAVs in the top of a disaster area such that the number of users served by the UAVs is maximized. The deployed UAV network ...
- research-articleMarch 2022
Iteration number-based hierarchical gradient aggregation for distributed deep learning
The Journal of Supercomputing (JSCO), Volume 78, Issue 4Pages 5565–5587https://doi.org/10.1007/s11227-021-04083-xAbstractDistributed deep learning can effectively accelerate neural model training, which employs multiple workers at a cluster of nodes to train a neural network in a parallel way. In this paper, we propose InHAD, an asynchronous distributed deep ...
- ArticleDecember 2021
FSAFA-stacking2: An Effective Ensemble Learning Model for Intrusion Detection with Firefly Algorithm Based Feature Selection
Algorithms and Architectures for Parallel ProcessingPages 555–570https://doi.org/10.1007/978-3-030-95388-1_37AbstractThis paper presents a two-layer ensemble learning model stacking2 based on the Stacking framework to deal with the problems of lack of generalization ability and low detection rate of single model intrusion detection system. The stacking2 uses ...
- ArticleAugust 2021
PFL-MoE: Personalized Federated Learning Based on Mixture of Experts
AbstractFederated learning (FL) is an emerging distributed machine learning paradigm that avoids data sharing among training nodes so as to protect data privacy. Under the coordination of the FL server, each client conducts model training using its own ...
- research-articleJune 2021
Double auction and profit maximization mechanism for jobs with heterogeneous durations in cloud federations
Journal of Cloud Computing: Advances, Systems and Applications (JOCCASA), Volume 10, Issue 1https://doi.org/10.1186/s13677-021-00249-3AbstractBy sharing resources with each other, different cloud providers in a cloud federation can exploit their diversity in resource configuration and operational cost so as to improve service performance. They should consider the strategy of resource ...
- research-articleAugust 2020
Dual-Way Gradient Sparsification for Asynchronous Distributed Deep Learning
ICPP '20: Proceedings of the 49th International Conference on Parallel ProcessingArticle No.: 49, Pages 1–10https://doi.org/10.1145/3404397.3404401Distributed parallel training using computing clusters is desirable for large scale deep neural networks. One of the key challenges in distributed training is the communication cost for exchanging information, such as stochastic gradients, among ...
- ArticleDecember 2019
Network Intrusion Detection Framework Based on Embedded Tree Model
Algorithms and Architectures for Parallel ProcessingPages 410–417https://doi.org/10.1007/978-3-030-38961-1_36AbstractNetwork intrusion detection system plays a vital role in network security protections that could be used to protect personal privacy and property security so as to protect users from attackers. However, there are a few samples of attack types with ...
- ArticleDecember 2019
Stable Clustering Algorithm for Routing Establishment in Vehicular Ad-Hoc Networks
Algorithms and Architectures for Parallel ProcessingPages 107–115https://doi.org/10.1007/978-3-030-38961-1_10AbstractWith regard to the complex and varied urban scenes in Vehicular Ad-Hoc Network, such as the vehicle nodes with fast speed, unstable links and frequent changes in network topology, this paper proposed a stable clustering algorithm to establish ...
- research-articleAugust 2019
COMBFT: Conflicting-Order-Match based Byzantine Fault Tolerance Protocol with High Efficiency and Robustness
ICPP '19: Proceedings of the 48th International Conference on Parallel ProcessingArticle No.: 68, Pages 1–10https://doi.org/10.1145/3337821.3337885Byzantine Fault-Tolerant (BFT) state machine replication protocol is an important building block for highly available distributed computing. This paper presents COMBFT, a BFT protocol that achieves both efficiency and robustness simultaneously. The ...