Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152749
Jialu Zhang, Xingguo Jiang, Yan Sun, Hong Luo
Joint extraction of entity and relation is a basic task in the field of natural language processing. Existing methods have achieved good result, but there are still some limitations, such as span-based extraction cannot solve overlapping problems well, and redundant relation calculation leads to many invalid operations. To solve these problems, we propose a novel RelationSpecific Triple Tagging and Scoring Model (RS-TTS) for the joint extraction of entity and relation. Specifically, the model is composed of three parts: we use a relation judgment module to predict all potential relations to prevent computational redundancy; then a boundary smoothing mechanism is introduced to the entity pair extraction, which reallocates the probability of the ground truth entity to its surrounding tokens, thus preventing the model from being overconfident; finally, an efficient tagging and scoring strategy is used to decode entity. Extensive experiments show that our model performs better than the state-of-the-art baseline on the public benchmark dataset. F1-scores on the four datasets are improved, especially on WebNLG and WebNLG∗, which are improved by 1.7 and 1.1 respectively.
{"title":"RS-TTS: A Novel Joint Entity and Relation Extraction Model","authors":"Jialu Zhang, Xingguo Jiang, Yan Sun, Hong Luo","doi":"10.1109/CSCWD57460.2023.10152749","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152749","url":null,"abstract":"Joint extraction of entity and relation is a basic task in the field of natural language processing. Existing methods have achieved good result, but there are still some limitations, such as span-based extraction cannot solve overlapping problems well, and redundant relation calculation leads to many invalid operations. To solve these problems, we propose a novel RelationSpecific Triple Tagging and Scoring Model (RS-TTS) for the joint extraction of entity and relation. Specifically, the model is composed of three parts: we use a relation judgment module to predict all potential relations to prevent computational redundancy; then a boundary smoothing mechanism is introduced to the entity pair extraction, which reallocates the probability of the ground truth entity to its surrounding tokens, thus preventing the model from being overconfident; finally, an efficient tagging and scoring strategy is used to decode entity. Extensive experiments show that our model performs better than the state-of-the-art baseline on the public benchmark dataset. F1-scores on the four datasets are improved, especially on WebNLG and WebNLG∗, which are improved by 1.7 and 1.1 respectively.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"33 1","pages":"71-76"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85081939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152773
JingQi Yang, Cheng Xie, Peng Tang
Zero-shot learning (ZSL) is an important research area in computer-supported cooperative work in design, especially in the field of visual collaborative computing. ZSL normally uses transferable semantic features to represent the visual features to predict unseen classes without training the unseen samples. Existing ZSL models have attempted to learn region features in a single image, while the discriminative attribute localization of visual features is typically neglected. To handle the mentioned problem, we propose a pre-trained Masked Autoencoders(MAE) based Zero-Shot Learning model. It uses multi-head self-attention in Transformer blocks to capture the most discriminative local features from a partial perspective by considering both positional and contextual information of the entire sequence of patches, which is consistent with the human attention mechanism when recognizing objects. Further, it uses a Multilayer Perceptron(MLP) to map visual features to the semantic space for relating visual and semantic attributes, and predicts the semantic information, which is used to find out the class label during inference. Both quantitative and qualitative experimental results on three popular ZSL benchmarks show the proposed method achieves the new state-of-the-art in the field of generalized zero-shot learning and conventional zero-shot learning. The source code of the proposed method is available at https://github.com/yangjingqi99/MAE-ZSL
{"title":"Discriminative Feature Focus via Masked Autoencoder for Zero-Shot Learning","authors":"JingQi Yang, Cheng Xie, Peng Tang","doi":"10.1109/CSCWD57460.2023.10152773","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152773","url":null,"abstract":"Zero-shot learning (ZSL) is an important research area in computer-supported cooperative work in design, especially in the field of visual collaborative computing. ZSL normally uses transferable semantic features to represent the visual features to predict unseen classes without training the unseen samples. Existing ZSL models have attempted to learn region features in a single image, while the discriminative attribute localization of visual features is typically neglected. To handle the mentioned problem, we propose a pre-trained Masked Autoencoders(MAE) based Zero-Shot Learning model. It uses multi-head self-attention in Transformer blocks to capture the most discriminative local features from a partial perspective by considering both positional and contextual information of the entire sequence of patches, which is consistent with the human attention mechanism when recognizing objects. Further, it uses a Multilayer Perceptron(MLP) to map visual features to the semantic space for relating visual and semantic attributes, and predicts the semantic information, which is used to find out the class label during inference. Both quantitative and qualitative experimental results on three popular ZSL benchmarks show the proposed method achieves the new state-of-the-art in the field of generalized zero-shot learning and conventional zero-shot learning. The source code of the proposed method is available at https://github.com/yangjingqi99/MAE-ZSL","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"10 1","pages":"417-422"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81352734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152626
Xiao-Min Hu, Yi Zhao, Zhuo Yang
Influence maximization (IM) aims to select a small number of seed users who can maximize the influence of information spread in social networks. The influence maximization problem in multiplex social networks considers the effects of overlapping users between different social networks on spreading the influence across networks. Since nodes in the network have different selection cost, the importance of a node cannot be determined only by the node's influence. This paper proposes a genetic algorithm using a novel node grouping strategy based on the node influence and selection cost, termed NGGA, for multiplex social networks. A node selection operation uses a shielding node set to realize a flexible search. Experimental results on three real multiplex networks demonstrate the effectiveness of the proposed algorithm.
{"title":"Nodes Grouping Genetic Algorithm for Influence Maximization in Multiplex Social Networks","authors":"Xiao-Min Hu, Yi Zhao, Zhuo Yang","doi":"10.1109/CSCWD57460.2023.10152626","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152626","url":null,"abstract":"Influence maximization (IM) aims to select a small number of seed users who can maximize the influence of information spread in social networks. The influence maximization problem in multiplex social networks considers the effects of overlapping users between different social networks on spreading the influence across networks. Since nodes in the network have different selection cost, the importance of a node cannot be determined only by the node's influence. This paper proposes a genetic algorithm using a novel node grouping strategy based on the node influence and selection cost, termed NGGA, for multiplex social networks. A node selection operation uses a shielding node set to realize a flexible search. Experimental results on three real multiplex networks demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"57 1","pages":"1130-1135"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81430558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152673
Chen Yang, Can Wang, Weidong Zhang, Huiyi Zhang, Xuangou Wu
With the development of blockchain technology, de-centralized applications (DApps) are increasingly being developed and deployed on blockchain platforms. However, the complex data validation mechanism and strict encryption protocol settings of blockchain often lead to sparse traffic behavior of DApps. This sparsity poses a challenge for existing encrypted traffic identification methods to extract distinguishable DApps traffic features. In this study, we propose a novel approach for identifying DApps traffic features by observing the differences in burst timing features of DApps. We introduce a continuous burst feature matrix (CBFM) method based on burst feature aggregation that can aggregate sparse features and express the burst timing differences of DApps encrypted traffic. Additionally, we design a deep learning classifier to automatically extract the features contained in the CBFM. Our experimental results on real datasets demonstrate that the proposed CBFM method achieves a classification accuracy of 94%, outperforming state-of-the-art methods.
{"title":"Decentralized Application Identification via Burst Feature Aggregation","authors":"Chen Yang, Can Wang, Weidong Zhang, Huiyi Zhang, Xuangou Wu","doi":"10.1109/CSCWD57460.2023.10152673","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152673","url":null,"abstract":"With the development of blockchain technology, de-centralized applications (DApps) are increasingly being developed and deployed on blockchain platforms. However, the complex data validation mechanism and strict encryption protocol settings of blockchain often lead to sparse traffic behavior of DApps. This sparsity poses a challenge for existing encrypted traffic identification methods to extract distinguishable DApps traffic features. In this study, we propose a novel approach for identifying DApps traffic features by observing the differences in burst timing features of DApps. We introduce a continuous burst feature matrix (CBFM) method based on burst feature aggregation that can aggregate sparse features and express the burst timing differences of DApps encrypted traffic. Additionally, we design a deep learning classifier to automatically extract the features contained in the CBFM. Our experimental results on real datasets demonstrate that the proposed CBFM method achieves a classification accuracy of 94%, outperforming state-of-the-art methods.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"21 1","pages":"1551-1556"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81539522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152744
Yin Xie, Yigui Luo, Haihong She, Zhaohong Xiang
In the past decade, computer vision has developed rapidly, and its application scenarios are increasing. But in the process of its application, the limited embedded compute capability is still one of the most important reasons hindering its development. In contrast, with the continuous improvement of mobile computing capability in recent years, the reasoning of neural network models on mobile phones has become a closer and closer fact. The most of tasks of computer vision are continuous and fixed order of the calculation processes. According to the characteristic, we propose a method for collaborative embedded inference on mobile phones. This method divides computer vision tasks, moves part of the calculation to the mobile phone, and runs in a pipeline scheme to achieve the effect of accelerating inference. This method can realize the running acceleration of such tasks and reducing the computational burden of the embedded platform. Codes are available at https://github.com/yiyexy/pipeline.
{"title":"Computation of Mobile Phone Collaborative Embedded Devices for Object Detection Task","authors":"Yin Xie, Yigui Luo, Haihong She, Zhaohong Xiang","doi":"10.1109/CSCWD57460.2023.10152744","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152744","url":null,"abstract":"In the past decade, computer vision has developed rapidly, and its application scenarios are increasing. But in the process of its application, the limited embedded compute capability is still one of the most important reasons hindering its development. In contrast, with the continuous improvement of mobile computing capability in recent years, the reasoning of neural network models on mobile phones has become a closer and closer fact. The most of tasks of computer vision are continuous and fixed order of the calculation processes. According to the characteristic, we propose a method for collaborative embedded inference on mobile phones. This method divides computer vision tasks, moves part of the calculation to the mobile phone, and runs in a pipeline scheme to achieve the effect of accelerating inference. This method can realize the running acceleration of such tasks and reducing the computational burden of the embedded platform. Codes are available at https://github.com/yiyexy/pipeline.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"54 1","pages":"778-783"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77062568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152654
Junnan Yin, Yuyan Sun, Lei Cui, Zhengyang Ai, Hongsong Zhu
Federated Learning (FL) is a promising machine learning paradigm for collaborative training on cross-soils in a privacy-protected manner. However, the existence of non-IID data causes problems such as performance degradation and thus becomes one of the key challenges in FL recently. To address this problem, we propose a clustered personalized federated learning method named as SynCPFL. SynCPFL groups clients sharing with the similar data distribution together, thereby facilitating collaboration and producing a better-personalized model for each client. In contrast to existing clustered federated learning methods, SynCPFL does not require multiple rounds of interaction between clients and server, so that the communication overhead is reduced a lot, thereby saving resources of clients. We evaluate SynCPFL on benchmark datasets, the experimental results demonstrate that SynCPFL outperforms existing methods.
{"title":"SynCPFL:Synthetic Distribution Aware Clustered Framework for Personalized Federated Learning","authors":"Junnan Yin, Yuyan Sun, Lei Cui, Zhengyang Ai, Hongsong Zhu","doi":"10.1109/CSCWD57460.2023.10152654","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152654","url":null,"abstract":"Federated Learning (FL) is a promising machine learning paradigm for collaborative training on cross-soils in a privacy-protected manner. However, the existence of non-IID data causes problems such as performance degradation and thus becomes one of the key challenges in FL recently. To address this problem, we propose a clustered personalized federated learning method named as SynCPFL. SynCPFL groups clients sharing with the similar data distribution together, thereby facilitating collaboration and producing a better-personalized model for each client. In contrast to existing clustered federated learning methods, SynCPFL does not require multiple rounds of interaction between clients and server, so that the communication overhead is reduced a lot, thereby saving resources of clients. We evaluate SynCPFL on benchmark datasets, the experimental results demonstrate that SynCPFL outperforms existing methods.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"13 5","pages":"438-443"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72545868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152706
Yuejia Wu, Jian-tao Zhou
Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models.
{"title":"A Graph Sequence Generator and Multi-head Self-attention Mechanism based Knowledge Graph Reasoning Architecture","authors":"Yuejia Wu, Jian-tao Zhou","doi":"10.1109/CSCWD57460.2023.10152706","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152706","url":null,"abstract":"Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"11 1","pages":"1520-1525"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75260639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The annotation for Chinese genealogy textual documents is helpful for constructing genealogy knowledge graph, training effective machine learning models for knowledge extraction, etc. However, this kind of documents is difficult to annotate. The primary reason is that the texts are written in both classical and vernacular Chinese. These texts also contain numerous ancient characters and are usually without punctuation. Understanding genealogy texts requires sufficient expertise. When multiple users labeling the same text, conflicts may occur. Existing annotation tools are inappropriate for this work. In this paper, we propose a novel interactive labeling tool, which provides text segmenting, entity and relationship tagging etc. With the annotated information, it is convenient to construct knowledge graph from textual documents, which can be used to analyze Chinese genealogy texts. Furthermore, we introduce a weak supervised mechanism with Hidden Markov Model for collaborative annotating with crowdsourcing. The practice shows that our approach is effective for collaborative annotation. It also facilitates the construction of knowledge graph and obtains more high-quality data sets. At present, this annotation tool has been applied into service.
{"title":"CAT: A Collaborative Annotation Tool for Chinese Genealogy Textual Documents","authors":"Huan Jiang, Zihao Wang, Rongrong Li, Yuwei Peng, Zhiyong Peng, Bin Xu","doi":"10.1109/CSCWD57460.2023.10152659","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152659","url":null,"abstract":"The annotation for Chinese genealogy textual documents is helpful for constructing genealogy knowledge graph, training effective machine learning models for knowledge extraction, etc. However, this kind of documents is difficult to annotate. The primary reason is that the texts are written in both classical and vernacular Chinese. These texts also contain numerous ancient characters and are usually without punctuation. Understanding genealogy texts requires sufficient expertise. When multiple users labeling the same text, conflicts may occur. Existing annotation tools are inappropriate for this work. In this paper, we propose a novel interactive labeling tool, which provides text segmenting, entity and relationship tagging etc. With the annotated information, it is convenient to construct knowledge graph from textual documents, which can be used to analyze Chinese genealogy texts. Furthermore, we introduce a weak supervised mechanism with Hidden Markov Model for collaborative annotating with crowdsourcing. The practice shows that our approach is effective for collaborative annotation. It also facilitates the construction of knowledge graph and obtains more high-quality data sets. At present, this annotation tool has been applied into service.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"18 1","pages":"1043-1048"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75427503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152637
Tianshuo Yang, Haibin Zhu
New employee training scheduling is one of the most common events in many enterprises. Solving this problem has its significance and is useful in daily administrations and operations. Group Role Assignment (GRA) model is widely applied in the assignment problem. However, there are still many challenges to applying the GRA model. For example, when we need to assign different jobs for the same person at different times, GRA needs more structures to specify constraints. If we use the strategy that combines the time factor with the agents or roles to formalize new agents or roles, the problem can be converted to a solvable GRA problem with constraints. The focus of this article is to give a practical solution to this kind of problem by using the GRA formulations in expressing constraints. The formalization makes us resolve the problem easily through integer programming (IP) with the PuLP package of Python. Large-scale simulation experiments demonstrate the practicability and robustness of our method.
{"title":"New Employee Training Scheduling Using the E-CARGO Model","authors":"Tianshuo Yang, Haibin Zhu","doi":"10.1109/CSCWD57460.2023.10152637","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152637","url":null,"abstract":"New employee training scheduling is one of the most common events in many enterprises. Solving this problem has its significance and is useful in daily administrations and operations. Group Role Assignment (GRA) model is widely applied in the assignment problem. However, there are still many challenges to applying the GRA model. For example, when we need to assign different jobs for the same person at different times, GRA needs more structures to specify constraints. If we use the strategy that combines the time factor with the agents or roles to formalize new agents or roles, the problem can be converted to a solvable GRA problem with constraints. The focus of this article is to give a practical solution to this kind of problem by using the GRA formulations in expressing constraints. The formalization makes us resolve the problem easily through integer programming (IP) with the PuLP package of Python. Large-scale simulation experiments demonstrate the practicability and robustness of our method.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"1 1","pages":"691-696"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72864670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152559
Zixuan Ma, Yuqi Zhang, Ruibang You, Chen Li
Software-Defined Networking (SDN) decouples the data plane from the control plane, enabling centralized control and open programmability of the network. OpenFlow flow rules are the key carrier for the SDN application to configure and manage the data plane through the control plane, and the processing efficiency of flow rules of the SDN controller in the control plane is critical as it will directly impact the instantaneity of configuring and managing the data plane. Currently, the controller increases the processing efficiency of flow rules by means of multi-threaded parallel processing. However, in the experiments of the widely used SDN controller ONOS, we found a new bottleneck in the parallel processing of flow rules that causes the performance gains from parallelism to be offset. Therefore, in this paper, we locate the bottleneck and analyze its causes through source code analysis and timestamp tests, propose a parallel event queue to resolve the bottleneck, and implement it in ONOS. Experiments show that our improved ONOS effectively resolves the bottleneck problem and achieves an average 3.57x improvement in the processing efficiency of flow rules compared to the original ONOS.
{"title":"Who Gets in the Way of Parallelism? Analysis and Optimization of the Parallel Processing Bottleneck of SDN Flow Rules in ONOS","authors":"Zixuan Ma, Yuqi Zhang, Ruibang You, Chen Li","doi":"10.1109/CSCWD57460.2023.10152559","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152559","url":null,"abstract":"Software-Defined Networking (SDN) decouples the data plane from the control plane, enabling centralized control and open programmability of the network. OpenFlow flow rules are the key carrier for the SDN application to configure and manage the data plane through the control plane, and the processing efficiency of flow rules of the SDN controller in the control plane is critical as it will directly impact the instantaneity of configuring and managing the data plane. Currently, the controller increases the processing efficiency of flow rules by means of multi-threaded parallel processing. However, in the experiments of the widely used SDN controller ONOS, we found a new bottleneck in the parallel processing of flow rules that causes the performance gains from parallelism to be offset. Therefore, in this paper, we locate the bottleneck and analyze its causes through source code analysis and timestamp tests, propose a parallel event queue to resolve the bottleneck, and implement it in ONOS. Experiments show that our improved ONOS effectively resolves the bottleneck problem and achieves an average 3.57x improvement in the processing efficiency of flow rules compared to the original ONOS.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"15 1","pages":"1808-1813"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88035385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：