2020 IEEE International Conference on Knowledge Graph (ICKG)最新文献_第3页

Causal Extraction from the Literature of Pressure Injury and Risk Factors 压力性损伤及危险因素的文献因果分析

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00087

Siyi Guo, Liuqi Jin, Jiaoyun Yang, M. Jiang, Lin Han, Ning An

{"title":"Causal Extraction from the Literature of Pressure Injury and Risk Factors","authors":"Siyi Guo, Liuqi Jin, Jiaoyun Yang, M. Jiang, Lin Han, Ning An","doi":"10.1109/ICBK50248.2020.00087","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00087","url":null,"abstract":"Literature for evidence on factors that put an individual at risk of pressure injury usually focused on identifying independent pressure injury risk factors. It is hard to find how important each factor is through the literature. By extracting casual relations, we can tackle the vast volume of causal knowledge and establish causal graphs. In this paper, we aim to use an unsupervised learning model to extract causal relations between pressure injury and risk factors. The workflow includes data preprocessing, causality determination, causality verification, and knowledge graph drawing. We conduct extensive experiments on a medical literature data set of 10,000 abstracts crawling from Pubmed and compare the knowledge graph we draw with the latest international guideline to verify the accuracy. We study 12 pressure injury risk factors and finally extract 10 relations between pressure injury and risk factors with the correct ratio 8/10, and 17 relations in the risk factor pairs with the correct ratio 16/17. The average credibility of extracting relations between pressure injury and risk factors is 0.7317, and 0.8983 for extracting relations of the 17 risk factor pairs. It indicates that the proposed method of extracting causal relations from the literature of pressure injury has a high degree of credibility.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124424675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Embedding-Based Entity Alignment Using Relation Structural Similarity 基于关系结构相似性的基于嵌入的实体对齐

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00027

Yanhui Peng, Jing Zhang, Cangqi Zhou, Jian Xu

{"title":"Embedding-Based Entity Alignment Using Relation Structural Similarity","authors":"Yanhui Peng, Jing Zhang, Cangqi Zhou, Jian Xu","doi":"10.1109/ICBK50248.2020.00027","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00027","url":null,"abstract":"Entity alignment aims to find entities in different knowledge graphs that semantically represent the same real-world entity. Recently, embedding-based entity alignment methods, which represent knowledge graphs as low-dimensional embeddings and perform entity alignments by measuring the similarity between entity embeddings, have achieved promising results. Most of these methods mainly focus on improving the knowledge graph embedding model or leveraging attributes to obtain more semantic information. However, the structural similarity between the two relations (considering all entities attached on the two relations) in different KGs has not been utilized in the existing methods. In this paper, we propose a novel embedding-based entity alignment method that takes the advantages of relation structural similarity. Specifically, our method first jointly learns the embeddings of two knowledge graphs in a uniform vector space, using the entity pairs regarding to the seed alignments (the alignments already known) that each shares the same embedding. Then, it iteratively computes the structural similarity between the relations in different knowledge graphs according to the seed alignments and the alignments with high reliability generated during training, which makes the embeddings of relations with high similarity closer to each other. Experimental results on five widely used real-world datasets show that the proposed approach significantly outperforms the state-of-the-art embedding-based ones for entity alignment.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132465733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Entity Spatio-temporal Evolution Summarization in Knowledge Graphs 知识图谱中的实体时空演化总结

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00035

Erhe Yang, Fei Hao, Jie Gao, Yulei Wu, G. Min

{"title":"Entity Spatio-temporal Evolution Summarization in Knowledge Graphs","authors":"Erhe Yang, Fei Hao, Jie Gao, Yulei Wu, G. Min","doi":"10.1109/ICBK50248.2020.00035","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00035","url":null,"abstract":"Knowledge graph has been growing in popularity with extensive applications in recent years, such as entity alignment, entity summarization, question answering, etc. However, the majority of research only focuses on one snapshot of the knowledge graph and neglects its dynamicity in nature, which often causes missing important information contained in other versions of the knowledge graph. Even worse, the incompleteness of the data in the knowledge graph is a challenge issue, which hinders the further utilization of the data. Considering that knowledge graph can evolve with time as well as the changing locations, it is necessary to summarize and integrate the entity temporal and spatial evolution information. To address this challenge, this paper pioneers to formulate the problem of entity spatio-temporal evolution summarization, capturing the entity evolution with time and location changes and integrating the data from two groups of various knowledge graphs. Further, we propose a two-stage approach: 1) generate entity temporal summarization and spatial summarization by utilizing the Triadic Formal Concept Analysis; 2) produce the spatio-temporal evolution summarization of the entity by adopting a fusion strategy. The obtained summarization results can be used to the visualization of the entity spatio-temporal evolution, data integration, and question answering.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133816042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fair Meta-Learning For Few-Shot Classification 公平元学习的少射分类

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00047

Chengli Zhao, Changbin Li, Jincheng Li, Feng Chen

{"title":"Fair Meta-Learning For Few-Shot Classification","authors":"Chengli Zhao, Changbin Li, Jincheng Li, Feng Chen","doi":"10.1109/ICBK50248.2020.00047","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00047","url":null,"abstract":"Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems. A machine learning algorithm trained based on biased data, however, tends to make unfair predictions. Developing classification algorithms that are fair with respect to protected attributes of the data thus becomes an important problem. Motivated by concerns surrounding the fairness effects of sharing and few-shot machine learning tools, such as the Model Agnostic Meta-Learning [1] framework, we propose a novel fair fast-adapted few-shot meta-learning approach that efficiently mitigates biases during meta-train by ensuring controlling the decision boundary covariance that between the protected variable and the signed distance from the feature vectors to the decision boundary. Through extensive experiments on two real-world image benchmarks over three state-of-the-art meta-learning algorithms, we empirically demonstrate that our proposed approach efficiently mitigates biases on model output and generalizes both accuracy and fairness to unseen tasks with a limited amount of training samples.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121265568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 19

Maintenance of Range Skyline Query 范围Skyline查询的维护

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00092

Xiaoxue Li, Yuanquan Shi, Xu Zhou, Kenli Li

引用次数: 1

Dynamic Relation Extraction with A Learnable Temporal Encoding Method 一种可学习时态编码方法的动态关系提取

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00042

Yinghan Shen, Xuhui Jiang, Yuanzhuo Wang, Xiaolong Jin, Xueqi Cheng

{"title":"Dynamic Relation Extraction with A Learnable Temporal Encoding Method","authors":"Yinghan Shen, Xuhui Jiang, Yuanzhuo Wang, Xiaolong Jin, Xueqi Cheng","doi":"10.1109/ICBK50248.2020.00042","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00042","url":null,"abstract":"The need to judge the relations between two entities at a specific time arises in many natural language understanding and knowledge graph related tasks, where the traditional relation extraction (RE) task without considering specific time is not feasible. Therefore, it is an important task to extract the dynamic relation from sentences containing the two entities. However, existing studies focus on extracting the static relation while ignoring temporal information in sentences or encode temporal information as a sequence to infer the relation. Considering these limitations of existing studies, we propose a Learnable Temporal Encoding (LTE) model, which encodes explicit temporal information in sentences. Specifically, we introduce a key-value memory network in LTE to identify the relation between an entity pair at a specific time. Through experiments on a general temporal relation extraction dataset, we show that the proposed model outperforms other state-of-the-art baselines, which demonstrate the effectiveness of LTE for dynamic relation extraction. We also conduct visual analysis to demonstrate that our model can fully represent the temporal information in the embedding space for any time spots.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116258258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Deep Reinforcement Learning for Greenhouse Climate Control 温室气候控制的深度强化学习

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00073

Lu Wang, Xiaofeng He, Dijun Luo

{"title":"Deep Reinforcement Learning for Greenhouse Climate Control","authors":"Lu Wang, Xiaofeng He, Dijun Luo","doi":"10.1109/ICBK50248.2020.00073","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00073","url":null,"abstract":"Worldwide, the area of greenhouse production is increasing with the rapid growth of global population and demands for fresh food. However, the greenhouse industry encounters challenges to find automatic control policy. Reinforcement Learning (RL) is a powerful tool in solving the autonomous decision making problems. In this paper, we propose a novel Deep Reinforcement Learning framework for cucumber climate control. Although some machine learning methods have been proposed to address the dynamic climate control problem, these methods have two major issues. First, they only consider the current reward (e.g., the fruit weight of the cucumber). Second, previous study only considers one control variable. However, the growth of crops are impacted by multiple factors synchronously (e.g., CO2 and Temperature).To solve these challenges, we propose a Deep Reinforcement learning based climate control method, which can model future reward explicitly. We further consider the fruit weight and the cost of the planting in order to improve the cumulative fruit weight and reduce the costs.Extensive experiments are conducted on the cucumber simulator environment have shown the superior performance of our methods.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127510544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

MM-GAN: 3D MRI Data Augmentation for Medical Image Segmentation via Generative Adversarial Networks MM-GAN:基于生成对抗网络的三维MRI数据增强医学图像分割

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00041

Yi Sun, Peisen Yuan, Yuming Sun

{"title":"MM-GAN: 3D MRI Data Augmentation for Medical Image Segmentation via Generative Adversarial Networks","authors":"Yi Sun, Peisen Yuan, Yuming Sun","doi":"10.1109/ICBK50248.2020.00041","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00041","url":null,"abstract":"Due to the limited amount of the labelled dataset, which hampers the training of deep architecture in medical imaging. The data augmentation is an effective way to extend the training dataset for medical image processing. However, subjective intervention is inevitable during this process, not only in the pertinent augmentation but also the non-pertinent augmentation. In this paper, to simulate the distribution of real data and sample new data from the distribution of limited data to populate the training set, we propose a generative adversarial network based architecture for the MRI augmentation and segmentation (MM-GAN), which can translate the label maps to 3D MR images without worrying about violating the pathology. Through a series of experiments of the tumor segmentation on BRATS17 dataset, we validate the effectiveness of MM-GAN in data augmentation and anonymization. Our approach improves the dice scores of the whole tumor and the tumor core by 0.17 and 0.16 respectively. With our method, only 29 samples are used for fine-tuning the model trained with the pure fake data and achieve comparable performance to the real data, which demonstrates the ability for the patient privacy protection. Furthermore, to verify the expandability of MM-GAN model, the dataset LIVER100 is collected. Experiment results on the LIVER100 illustrate similar outcome as on BRATS17, which validates the performance of our model.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126232863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 24

Neural Entity Synonym Set Generation using Association Information and Entity Constraint 基于关联信息和实体约束的神经实体同义词集生成

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00053

Subin Huang, Xiangfeng Luo, Jing Huang, Wei Qin, Shengwei Gu

{"title":"Neural Entity Synonym Set Generation using Association Information and Entity Constraint","authors":"Subin Huang, Xiangfeng Luo, Jing Huang, Wei Qin, Shengwei Gu","doi":"10.1109/ICBK50248.2020.00053","DOIUrl":"https://doi.org/10.1109/ICBK50248.2020.00053","url":null,"abstract":"Automatically generating entity synonym sets (i.e., sets of terms that represent the same entity) is an important work for many entity-based tasks. Existing studies on entity synonym set generation either use a ranking plus pruning approach or take the problem as a two-phase task (i.e., extracting synonymy pairs, subsequently organizing these pairs into synonym sets). However, these approaches ignore the association semantics of entities and suffer from the error propagation issue. In this paper, we propose a neural-network-based entity synonym set generation approach that exploits association information and entity constraint to generate synonym sets from a given term (i.e., entity) vocabulary. Firstly, to learn whether a new term should be added into the synonym set, an association-aware set-term neural network classifier is proposed. In the classifier, not only the entity representations but also the entity association information is exploited for extracting synonymous features. Secondly, an entity-constraint-based synonym set generation algorithm is employed to apply the trained set-term neural network classifier to generate the entity synonym sets from the term vocabulary. Finally, we conduct the proposed approach on three real-world datasets. The experimental results demonstrate that the entity synonym set generation performance of the proposed approach is better than that of the compared approaches.","PeriodicalId":432857,"journal":{"name":"2020 IEEE International Conference on Knowledge Graph (ICKG)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128171475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Periodic Guidance Learning 定期指导学习

2020 IEEE International Conference on Knowledge Graph (ICKG) Pub Date : 2020-08-01 DOI: 10.1109/ICBK50248.2020.00021

Lipeng Wan, Xuguang Lan, Xuwei Song, Chuzhen Feng, Nanning Zheng

引用次数: 0