分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2024-03-16
摘要： A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning algorithms and pruning techniques, effectively addressing the inefficiencies of traditional federated learning algorithms in scenarios involving heterogeneous devices, as well as tackling the staleness issue and inadequate training of certain clients in asynchronous algorithms. Through the incremental restoration of model size during training, the framework expedites model training while preserving model accuracy. Furthermore, enhancements to the federated learning aggregation process are introduced, incorporating a buffering mechanism to enable asynchronous federated learning to operate akin to synchronous learning. Additionally, optimizations in the process of the server transmitting the global model to clients reduce communication overhead. Our experiments across various datasets demonstrate that: (i) significant reductions in training time and improvements in convergence accuracy are achieved compared to conventional asynchronous FL and HeteroFL; (ii) the advantages of our approach are more pronounced in scenarios with heterogeneous clients and non-IID client data.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2024-01-07
摘要： 由于人工神经网络具有高度非线性描述的特点，这个特点导致了他们被愈来愈广泛的研究和应用，在这些研究和应用当中主要的应用领域就是分类。分类实现的基础是特征分类，所以要进行分类就需要先提取样本的特征。在常见的卷积神经网络中，通常是由输入层、卷积层、池化层、激活层、全连接层，按照一定的次序连接而构成。卷积神经网络的输入层实现的是整个神经网络的输入，在本设计中，训练和推理的数据为30*30像素的单通道灰度图
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2023-02-16
摘要： Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays precipitously as the number of training samples decreases when there is insufficient data. (3) Model trained on sample-balanced datasets still has different biases for different classes. In this work, we define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. It is exciting to find experimentally that there is a marginal effect of semantic scale, which perfectly describes the first two phenomena. Further, the quantitative measurement of semantic scale imbalance is proposed, which can accurately reflect model bias on multiple datasets, even on sample-balanced data, revealing a novel perspective for the study of class imbalance. Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets, which is a good starting point for mitigating the prevalent but unnoticed model bias. In addition, we look ahead to future challenges.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2023-02-16
摘要： Real-world data are long-tailed, the lack of tail samples leads to a significant limitation in the generalization ability of the model. Although numerous approaches of class re-balancing perform well for moderate class imbalance problems, additional knowledge needs to be introduced to help the tail class recover the underlying true distribution when the observed distribution from a few tail samples does not represent its true distribution properly, thus allowing the model to learn valuable information outside the observed domain. In this work, we propose to leverage the geometric information of the feature distribution of the well-represented head class to guide the model to learn the underlying distribution of the tail class. Specifically, we first systematically define the geometry of the feature distribution and the similarity measures between the geometries, and discover four phenomena regarding the relationship between the geometries of different feature distributions. Then, based on four phenomena, feature uncertainty representation is proposed to perturb the tail features by utilizing the geometry of the head class feature distribution. It aims to make the perturbed features cover the underlying distribution of the tail class as much as possible, thus improving the models generalization performance in the test domain. Finally, we design a three-stage training scheme enabling feature uncertainty modeling to be successfully applied. Experiments on CIFAR-10/100-LT, ImageNet-LT, and iNaturalist2018 show that our proposed approach outperforms other similar methods on most metrics. In addition, the experimental phenomena we discovered are able to provide new perspectives and theoretical foundations for subsequent studies. The code will be available at https://github.com/mayanbiao1234/Geometric-Prior
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2023-02-15 合作期刊: 《桂林电子科技大学学报》
摘要： 传统网络越发难以面对复杂化的网络结构,于是诞生了一种新型网络架构,即软件定义网络(SDN)。SDN数据中 心的业务流主要有长流和短流,长流有持续时间长、时延不敏感、带宽需求高的特点;而短流持续时间短、时延敏感程度高、 带宽需求低。短流的流量占总流量不足20%,但流量条数则约占总流量数的80%以上;长流的流量占总流量80%以上,但 流量条数不足总流量数的20%。研究发现,在出端口队列中长流往往在短流前,造成短流长时间等待,极易引发网络拥塞。 根据2种业务流特点提出排队机制和路由优化保障机制,将短流设置为高优先级队列,由SDN控制器优先调度排队机制; 将长流设置为低优先级队列,同时采用路由保障算法进行补偿。路由保障算法首先删除不满足长流带宽需求的链路,再计 算最短时延路径。为了提升本设计的算法效率,使用FPGA和万兆以太网对SDN中业务流进行仿真,并在FPGA上仿真 验证了本设计对于网络的时延、带宽的优化与FPGA并行运算的优势。
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-29 合作期刊: 《数据智能（英文）》
摘要： Reproducibility is a cornerstone of scientific research. Data science is not an exception. In recent years scientists were concerned about a large number of irreproducible studies. Such reproducibility crisis in science could severely undermine public trust in science and science-based public policy. Recent efforts to promote reproducible research mainly focused on matured scientists and much less on student training. In this study, we conducted action research on students in data science to evaluate to what extent students are ready for communicating reproducible data analysis. The results show that although two-thirds of the students claimed they were able to reproduce results in peer reports, only one-third of reports provided all necessary information for replication. The actual replication results also include conflicting claims; some lacked comparisons of original and replication results, indicating that some students did not share a consistent understanding of what reproducibility means and how to report replication results. The findings suggest that more training is needed to help data science students communicating reproducible data analysis.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-29 合作期刊: 《数据智能（英文）》
摘要： It is easy to argue that open data is critical to enabling faster and more effective research discovery. In this article, we describe the approach we have taken at Wiley to support open data and to start enabling more data to be FAIR data (Findable, Accessible, Interoperable and Reusable) with the implementation of four data policies: Encourages, Expects, Mandates and Mandates and Peer Reviews Data. We describe the rationale for these policies and levels of adoption so far. In the coming months we plan to measure and monitor the implementation of these policies via the publication of data availability statements and data citations. With this information, well be able to celebrate adoption of data-sharing practices by the research communities we work with and serve, and we hope to showcase researchers from those communities leading in open research.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-29 合作期刊: 《数据智能（英文）》
摘要： Over the past five years, Elsevier has focused on implementing FAIR and best practices in data management, from data preservation through reuse. In this paper we describe a series of efforts undertaken in this time to support proper data management practices. In particular, we discuss our journal data policies and their implementation, the current status and future goals for the research data management platform Mendeley Data, and clear and persistent linkages to individual data sets stored on external data repositories from corresponding published papers through partnership with Scholix. Early analysis of our data policies implementation confirms significant disparities at the subject level regarding data sharing practices, with most uptake within disciplines of Physical Sciences. Future directions at Elsevier include implementing better discoverability of linked data within an article and incorporating research data usage metrics.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-29 合作期刊: 《数据智能（英文）》
摘要： Knowledge graph (KG) has played an important role in enhancing the performance of many intelligent systems. In this paper, we introduce the solution of building a large-scale multi-source knowledge graph from scratch in Sogou Inc., including its architecture, technical implementation and applications. Unlike previous works that build knowledge graph with graph databases, we build the knowledge graph on top of SogouQdb, a distributed search engine developed by Sogou Web Search Department, which can be easily scaled to support petabytes of data. As a supplement to the search engine, we also introduce a series of models to support inference and graph based querying. Currently, the data of Sogou knowledge graph that are collected from 136 different websites and constantly updated consist of 54 million entities and over 600 million entity links. We also introduce three applications of knowledge graph in Sogou Inc.: entity detection and linking, knowledge based question answering and knowledge based dialogue system. These applications have been used in Web search products to help user acquire information more efficiently.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-29 合作期刊: 《数据智能（英文）》
摘要： For many government departments, uncertainty aversion is a source of barriers in the advancement of data openness. A more active response to potential risks is needed and necessitates an in-depth examination of risks related to open government data (OGD). With a cross-case study in which three cases from the United Kingdom, the United States and China are examined, this study identifies potential risks that might emerge at different stages of the lifecycle of OGD programs and constructs a taxonomy model for them. The taxonomy model distinguishes the risks from OGD from the risks to OGD, which can help government departments make better responses. Finally, risk response strategies are suggested based on the research results.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： Multi-modal entity linking plays a crucial role in a wide range of knowledge-based modal-fusion tasks, i.e., multi-modal retrieval and multi-modal event extraction. We introduce the new ZEro-shot Multi-modal Entity Linking (ZEMEL) task, the format is similar to multi-modal entity linking, but multi-modal mentions are linked to unseen entities in the knowledge graph, and the purpose of zero-shot setting is to realize robust linking in highly specialized domains. Simultaneously, the inference efficiency of existing models is low when there are many candidate entities. On this account, we propose a novel model that leverages visual#2; linguistic representation through the co-attentional mechanism to deal with the ZEMEL task, considering the trade-off between performance and efficiency of the model. We also build a dataset named ZEMELD for the new task, which contains multi-modal data resources collected from Wikipedia, and we annotate the entities as ground truth. Extensive experimental results on the dataset show that our proposed model is effective as it significantly improves the precision from 68.93% to 82.62% comparing with baselines in the ZEMEL task.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： In this study, we uncover the topics of Chinese public cultural activities in 2020 with a two-step short text clustering (self-taught neural networks and graph-based clustering) and topic modeling approach. The dataset we use for this research is collected from 108 websites of libraries and cultural centers, containing over 17,000 articles. With the novel framework we propose, we derive 3 clusters and 8 topics from 21 provincial#2; level regions in China. By plotting the topic distribution of each cluster, we are able to shows unique tendencies of local cultural institutes, that is, free lessons and lectures on art and culture, entertainment and service for socially vulnerable groups, and the preservation of intangible cultural heritage respectively. The findings of our study provide decision-making support for cultural institutes, thus promoting public cultural service from a data-driven perspective.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： The research on graph pattern matching (GPM) has attracted a lot of attention. However, most of the research has focused on complex networks, and there are few researches on GPM in the medical field. Hence, with GPM this paper is to make a breast cancer-oriented diagnosis before the surgery. Technically, this paper has firstly made a new definition of GPM, aiming to explore the GPM in the medical field, especially in Medical Knowledge Graphs (MKGs). Then, in the specific matching process, this paper introduces fuzzy calculation, and proposes a multi-threaded bidirectional routing exploration (M-TBRE) algorithm based on depth first search and a two-way routing matching algorithm based on multi-threading. In addition, fuzzy constraints are introduced in the M-TBRE algorithm, which leads to the Fuzzy-M-TBRE algorithm. The experimental results on the two datasets show that compared with existing algorithms, our proposed algorithm is more efficient and effective.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： Relational extraction plays an important role in the field of natural language processing to predict semantic relationships between entities in a sentence. Currently, most models have typically utilized the natural language processing tools to capture high-level features with an attention mechanism to mitigate the adverse effects of noise in sentences for the prediction results. However, in the task of relational classification, these attention mechanisms do not take full advantage of the semantic information of some keywords which have information on relational expressions in the sentences. Therefore, we propose a novel relation extraction model based on the attention mechanism with keywords, named Relation Extraction Based on Keywords Attention (REKA). In particular, the proposed model makes use of bi-directional GRU (Bi-GRU) to reduce computation, obtain the representation of sentences , and extracts prior knowledge of entity pair without any NLP tools. Besides the calculation of the entity-pair similarity, Keywords attention in the REKA model also utilizes a linear-chain conditional random field (CRF) combining entity-pair features, similarity features between entity-pair features, and its hidden vectors, to obtain the attention weight resulting from the marginal distribution of each word. Experiments demonstrate that the proposed approach can utilize keywords incorporating relational expression semantics in sentences without the assistance of any high-level features and achieve better performance than traditional methods.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： Artificial intelligence and machine learning applications are of significant importance almost in every field of human life to solve problems or support human experts. However, the determination of the machine learning model to achieve a superior result for a particular problem within the wide real-life application areas is still a challenging task for researchers. The success of a model could be affected by several factors such as dataset characteristics, training strategy and model responses. Therefore, a comprehensive analysis is required to determine model ability and the efficiency of the considered strategies. This study implemented ten benchmark machine learning models on seventeen varied datasets. Experiments are performed using four different training strategies 60:40, 70:30, and 80:20 hold-out and five-fold cross-validation techniques. We used three evaluation metrics to evaluate the experimental results: mean squared error, mean absolute error, and coefficient of determination (R2 score). The considered models are analyzed, and each model's advantages, disadvantages, and data dependencies are indicated. As a result of performed excess number of experiments, the deep Long-Short Term Memory (LSTM) neural network outperformed other considered models, namely, decision tree, linear regression, support vector regression with a linear and radial basis function kernels, random forest, gradient boosting, extreme gradient boosting, shallow neural network, and deep neural network. It has also been shown that cross-validation has a tremendous impact on the results of the experiments and should be considered for the model evaluation in regression studies where data mining or selection is not performed.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： COVID-19 evolves rapidly and an enormous number of people worldwide desire instant access to COVID- 19 information such as the overview, clinic knowledge, vaccine, prevention measures, and COVID-19 mutation. Question answering (QA) has become the mainstream interaction way for users to consume the ever-growing information by posing natural language questions. Therefore, it is urgent and necessary to develop a QA system to offer consulting services all the time to relieve the stress of health services. In particular, people increasingly pay more attention to complex multi-hop questions rather than simple ones during the lasting pandemic, but the existing COVID-19 QA systems fail to meet their complex information needs. In this paper, we introduce a novel multi-hop QA system called COKG-QA, which reasons over multiple relations over large-scale COVID-19 Knowledge Graphs to return answers given a question. In the field of question answering over knowledge graph, current methods usually represent entities and schemas based on some knowledge embedding models and represent questions using pre-trained models. While it is convenient to represent different knowledge (i.e., entities and questions) based on specified embeddings, an issue raises that these separate representations come from heterogeneous vector spaces. We align question embeddings with knowledge embeddings in a common semantic space by a simple but effective embedding projection mechanism. Furthermore, we propose combining entity embeddings with their corresponding schema embeddings which served as important prior knowledge, to help search for the correct answer entity of specified types. In addition, we derive a large multi-hop Chinese COVID-19 dataset (called COKG-DATA for remembering) for COKG-QA based on the linked knowledge graph OpenKG-COVID19 launched by OpenKG, including comprehensive and representative information about COVID-19. COKG-QA achieves quite competitive performance in the 1-hop and 2-hop data while obtaining the best result with significant improvements in the 3-hop. And it is more efficient to be used in the QA system for users. Moreover, the user study shows that the system not only provides accurate and interpretable answers but also is easy to use and comes with smart tips and suggestions.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a certain aspect of semantic features, for example, CNN on long-range dependencies part, Transformer on local features. It is difficult for a single model to adapt to various relation learning, which results in a high variance problem. Ensemble strategy could be competitive in improving the accuracy of few-shot relation extraction and mitigating high variance risks. This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features. Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： Temporal information is pervasive and crucial in medical records and other clinical text, as it formulates the development process of medical conditions and is vital for clinical decision making. However, providing a holistic knowledge representation and reasoning framework for various time expressions in the clinical text is challenging. In order to capture complex temporal semantics in clinical text, we propose a novel Clinical Time Ontology (CTO) as an extension from OWL framework. More specifically, we identified eight time#2; related problems in clinical text and created 11 core temporal classes to conceptualize the fuzzy time, cyclic time, irregular time, negations and other complex aspects of clinical time. Then, we extended Allens and TEOs temporal relations and defined the relation concept description between complex and simple time. Simultaneously, we provided a formulaic and graphical presentation of complex time and complex time relationships. We carried out empirical study on the expressiveness and usability of CTO using real-world healthcare datasets. Finally, experiment results demonstrate that CTO could faithfully represent and reason over 93% of the temporal expressions, and it can cover a wider range of time-related classes in clinical domain.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
摘要： A growing interest in producing and sharing computable biomedical knowledge artifacts (CBKs) is increasing the demand for repositories that validate, catalog, and provide shared access to CBKs. However, there is a lack of evidence on how best to manage and sustain CBK repositories. In this paper, we present the results of interviews with several pioneering CBK repository owners. These interviews were informed by the Trusted Repositories Audit and Certification (TRAC) framework. Insights gained from these interviews suggest that the organizations operating CBK repositories are somewhat new, that their initial approaches to repository governance are informal, and that achieving economic sustainability for their CBK repositories is a major challenge. To enable a learning health system to make better use of its data intelligence, future approaches to CBK repository management will require enhanced governance and closer adherence to best practice frameworks to meet the needs of myriad biomedical science and health communities. More effort is needed to find sustainable funding models for accessible CBK artifact collections.
分类： 计算机科学 >> 计算机科学的集成理论 提交时间： 2022-11-28 合作期刊: 《数据智能（英文）》
Abraham, Nieva de la Hidalga
Donato, Decarolis
Shaojun, Xu
Santhosh, Matam
Willinton, Yesid Hernández Enciso
Josephine, Goodall
Brian, Matthews
C. Richard, A. Catlow
摘要： The UK Catalysis Hub (UKCH) is designing a virtual research environment to support data processing and analysis, the Catalysis Research Workbench (CRW). The development of this platform requires identifying the processing and analysis needs of the UKCH members and mapping them to potential solutions. This paper presents a proposal for a demonstrator to analyse the use of scientific workflows for large scale data processing. The demonstrator provides a concrete target to promote further discussion of the processing and analysis needs of the UKCH community. In this paper, we will discuss the main requirements for data processing elicited and the proposed adaptations that will be incorporated in the design of the CRW and how to integrate the proposed solutions with existing practices of the UKCH. The demonstrator has been used in discussion with researchers and in presentations to the UKCH community, generating increased interest and motivating further development.
点击量
待评议
点击量
下载量
评论
通过
