知识图谱(Knowledge Graphs,KGs)中的特征选择正越来越多地应用于生物医学研究、自然语言处理(Natural Language Processing,NLP)、个性化推荐系统等多个领域。本文深入研究了知识图谱内的特征选择方法,重点阐述其在提升机器学习(machine learning,ML)模型效能、生成假设及增强可解释性方面的作用。通过本次全面综述,我们旨在推动知识图谱特征选择领域的进一步创新,为各领域中更具洞察力、更高效且可解释性更强的分析模型奠定基础。我们的研究揭示了可扩展性、准确性和可解释性在特征选择技术中的关键作用,主张融入领域知识以优化选择过程。我们强调了多目标优化与跨学科合作在推进知识图谱特征选择方面日益凸显的潜力,着重指出这类方法对精准医学等领域具有变革性影响。本文最后规划了未来研究方向,包括开发可扩展的动态特征选择算法,以及融入可解释AI原则以提升知识图谱驱动模型的透明度与可信度。
英文摘要:
Feature selection in Knowledge Graphs (KGs) are increasingly utilized in diverse domains, including biomedical research, Natural Language Processing (NLP), and personalized recommendation systems. This paper delves into the methodologies for feature selection within KGs, emphasizing their roles in enhancing machine learning (ML) model efficacy, hypothesis generation, and interpretability. Through this comprehensive review, we aim to catalyze further innovation in feature selection for KGs, paving the way for more insightful, efficient, and interpretable analytical models across various domains. Our exploration reveals the critical importance of scalability, accuracy, and interpretability in feature selection techniques, advocating for the integration of domain knowledge to refine the selection process. We highlight the burgeoning potential of multi-objective optimization and interdisciplinary collaboration in advancing KG feature selection, underscoring the transformative impact of such methodologies on precision medicine, among other fields. The paper concludes by charting future directions, including the development of scalable, dynamic feature selection algorithms and the integration of explainable AI principles to foster transparency and trust in KG-driven models.
Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review
Shanghai Jiao Tong University(上海交通大学);Georgia Institute of Technology(佐治亚理工学院);Shanghai AI Laboratory(上海人工智能实验室);University of Georgia(佐治亚大学);Oxford University(牛津大学)
Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategies
Hong Kong Baptist University(香港浸会大学);BNU-UIC Institute of AI and Future Networks(北师大-联合国际学院人工智能与未来网络研究院);BNU-HKBU United International College(北师大-港浸大联合国际学院);Beijing Normal University(北京师范大学)
A Review on Single-Problem Multi-Attempt Heuristic Optimization
BCAM - Basque Center for Applied Mathematics(巴斯克应用数学中心);UPV/EHU - University of the Basque Country(巴斯克国家大学);NTNU - Norwegian University of Science and Technology(挪威科学技术大学)
Artificial Intelligence-Assisted Energy and Thermal Comfort Control for Sustainable Buildings: An Extended Representation of the Systematic Review
Mohammed V University of Rabat(拉巴特穆罕默德五世大学);MENTIS SA(MENTIS SA公司);University of Nebraska at Kearney (UNK)(内布拉斯加大学凯尔尼分校);Information Technology University(信息技术大学);Alfaisal University(费萨尔国王大学);Hamad Bin Khalifa University(哈马德·本·哈利法大学);Western Michigan University(西密歇根大学);Alakhawayn University in Ifrane(伊夫兰阿赫瓦因大学);University of Houston(休斯顿大学)
不同的因素,如热舒适度,湿度,空气质量和噪音有显着的综合影响的可接受性和质量的活动进行的建筑物居住者谁花了他们的大部分时间在室内。在所引用的因素中,热舒适性有助于人类的福祉,因为它与人体的温度调节有关。因此,创造热舒适和节能的环境在建筑物的设计中非常重要,因此供暖,通风和空调系统也非常重要。最近的工作已经针对更先进的控制策略,主要是基于人工智能,具有模仿人类行为的能力。本文系统地综述了建筑物内的智能控制策略,并探讨了它们在室内环境中平衡热舒适性和节能优化的能力。方法.系统的文献综述使用ACM数字图书馆,Scopus,Google Scholar,IEEE Xplore(IEOL),Web of Science和Science Direct(SDOL)以及手动搜索的其他来源检查了同行评审的研究作品。包含以下字符串术语:热舒适性、舒适温度、首选温度、智能控制、高级控制、人工智能、计算智能、建筑、室内和建筑环境。入选标准为:英国,研究监测,主要是在建筑物中的人体热舒适性和能源效率同时基于控制策略,使用智能方法。使用系统性综述和荟萃分析指南的首选报告项目。最初,产生了1,077篇文章,最终有120篇符合纳入标准并进行了审查。