Demographic data, such as income, education level, and employment rate, contain valuable information of urban regions, yet few studies have integrated demographic information to generate region embedding. In this study, we show how the simple and easy-to-access demographic data can improve the quality of state-of-the-art region embedding and provide better predictive performances in urban areas across three common urban tasks, namely check-in prediction, crime rate prediction, and house price prediction. We find that existing pre-train methods based on KL divergence are potentially biased towards mobility information and propose to use Jenson-Shannon divergence as a more appropriate loss function for multi-view representation learning. Experimental results from both New York and Chicago show that mobility + income is the best pre-train data combination, providing up to 10.22\% better predictive performances than existing models. Considering that mobility big data can be hardly accessible in many developing cities, we suggest geographic proximity + income to be a simple but effective data combination for region embedding pre-training.
Demographic Predictability in 3D CT Foundation Embeddings
Rice University(莱斯大学);McGovern Medical School, UTHealth Houston(德克萨斯大学休斯顿健康科学中心麦戈文医学院);Johns Hopkins University School of Medicine(约翰霍普金斯大学医学院);University of Maryland School of Medicine(马里兰大学医学院)
Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications
Wright State University(莱特州立大学);Cincinnati Children’s Hospital Medical Center(辛辛那提儿童医院医疗中心);Kairos Research LLC(Kairos Research有限责任公司);University of Illinois Chicago(伊利诺伊大学芝加哥分校)
Towards Fair Medical AI: Adversarial Debiasing of 3D CT Foundation Embeddings
Rice University(莱斯大学);The Johns Hopkins University(约翰斯·霍普金斯大学);McGovern Medical School, UTHealth Houston(德克萨斯大学健康科学中心休斯顿分校麦戈文医学院);The Johns Hopkins University School of Medicine(约翰斯·霍普金斯大学医学院);Sidney Kimmel Comprehensive Cancer Center, The Johns Hopkins University School of Medicine(约翰斯·霍普金斯大学医学院西德尼·基梅尔综合癌症中心);Google Research(谷歌研究院);Department of Neurosurgery, The Johns Hopkins University School of Medicine(约翰斯·霍普金斯大学医学院神经外科)
3D Facial Matching by Spiral Convolutional Metric Learning and a Biometric Fusion-Net of Demographic Properties
KU Leuven(天主教鲁汶大学);Imperial College London(伦敦帝国学院);USI Lugano(卢加诺大学);Indiana University-Purdue University-Indianapolis(印第安纳大学-普渡大学印第安纳波利斯联合分校);Penn State University(宾夕法尼亚州立大学);Twitter(推特)
Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records
University of Bonn(波恩大学)
由电子病历构建的医学知识图谱包含了丰富的患者和医疗实体信息。KG嵌入模型在这些数据上的利用已被证明对于不同的医疗任务是有效的。然而,现有的模型没有适当地纳入患者的人口统计数据,他们中的大多数忽略了医疗KG的概率特征。在本文中,我们提出了DARLING(人口统计学感知pRobabiListic medIcal kNowledge embeddinG),一个人口统计学感知的医疗KG嵌入框架,通过将患者人口统计数据与相应的超平面相关联,明确地将人口统计数据纳入医疗实体空间。我们的框架利用医疗实体内的概率特征,通过人口统计学指导来学习它们的表示。我们评估DARLING通过链接预测的治疗和药物,从EMR数据构建的医疗KG,并说明其优越的性能相比,现有的KG嵌入模型。
Region Embedding with Intra and Inter-View Contrastive Learning
Nanyang Technological University(南洋理工大学)
无监督区域表示学习旨在从未标记的城市数据中提取密集有效的特征。虽然已经基于多个视图做出了一些努力来解决这个问题,但是现有方法在提取视图中的表示和/或合并来自不同视图的表示方面仍然不足。基于对比学习在表示学习中的成功,我们提出将其用于多视图区域表示学习,并设计了一个称为ReMVC(Region Embedding with Multi-View对比学习)的模型,该模型遵循两个指导原则:i)在每个视图中将区域与其他区域进行比较,以实现有效的表征提取; ii)在不同视图中将区域与自身进行比较,以实现跨视图信息共享。我们设计了视图内对比学习模块和视图间对比学习模块,前者用于学习不同的区域嵌入,后者作为软共正则化器来约束嵌入参数并在多视图间传递知识。我们在两个下游任务中利用学习到的区域嵌入,即土地使用聚类和区域流行度预测。大量的实验表明,我们的模型实现了令人印象深刻的改进相比,七个国家的最先进的基线方法,在土地利用聚类任务的利润率超过30%。
Analyzing the Impact of Foursquare and Streetlight Data with Human Demographics on Future Crime Prediction
Dalhousie University(达尔豪斯大学);Universidade Federal de Santa Catarina(圣卡塔琳娜联邦大学);Memorial University of Newfoundland(纽芬兰纪念大学);Polish Academy of Sciences(波兰科学院)
Demographic Inference and Representative Population Estimates from Multilingual Social Media Data
Stanford University(斯坦福大学);University of Michigan(密歇根大学);University of Oxford(牛津大学);Alan Turing Institute(艾伦·图灵研究所);MPI-SWS(马克斯·普朗克软件系统研究所);Saarland University(萨尔兰大学);University of Massachusetts(马萨诸塞大学);GESIS Cologne(GESIS科隆社会科学研究所)
Radiology Report Generation Using Transformers Conditioned with Non-imaging Data
Centre for Computational Imaging and Simulation Technologies in Biomedicine(生物医学计算成像与模拟技术中心);Leeds Institute for Cardiovascular and Metabolic Medicine(利兹心血管与代谢医学研究所);School of Medicine(医学院);School of Computing, University of Leeds(利兹大学计算机学院)
本文提出一种多模态 Transformer 网络,整合胸部 X 射线图像与患者人口统计信息生成放射报告,实验证明加入非影像数据有效提升了生成质量。