检索结果-内蒙古大学图书馆

Captions Speak Louder than Images (CASLIE): Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ling, Xinyi Peng, Bo Du, Hanwen Zhu, Zhihui Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States

Leveraging multimodal data to drive breakthroughs in e-commerce applications through Multimodal Foundation Models (MFMs) is gaining increasing attention from the research community. However, there are significant challenges that hinder the optimal use of multimodal e-commerce data by foundation models: (1) the scarcity of large-scale, high-quality multimodal benchmark datasets;and (2) the lack of effective multimodal information integration methods. To address these challenges, in this paper, we introduce MMECInstruct, the first-ever, large-scale, and high-quality multimodal instruction dataset for e-commerce. We also develop CASLIE, a simple, lightweight, yet effective framework for integrating multimodal information for e-commerce. Leveraging MMECInstruct, we fine-tune a series of e-commerce MFMs within CASLIE, denoted as CASLIE models. Our comprehensive evaluation demonstrates that CASLIE models substantially outperform 5 categories of advanced baseline models in the in-domain evaluation. Moreover, CASLIE models show strong generalizability to out-of-domain settings. MMECInstruct and CASLIE models are publicly accessible through https://***/CASLIE/. © 2024, CC BY.

关键词： Large datasets

Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Peng, Bo Burns, Ben Chen, Ziqi Parthasarathy, Srinivasan Ning, Xia Department of Computer Science and Engineering The Ohio State University Columbus United States Department of Biomedical Informatics The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

In recent years, with large language models (LLMs) achieving state-of-the-art performance in context understanding, increasing efforts have been dedicated to developing LLM-enhanced sequential recommendation (SR) methods. Considering that most existing LLMs are not specifically optimized for recommendation tasks, adapting them for SR becomes a critical step in LLM-enhanced SR methods. Though numerous adaptation methods have been developed, it still remains a significant challenge to adapt LLMs for SR both efficiently and effectively. To address this challenge, in this paper, we introduce a novel side sequential network adaptation method, denoted as SSNA, for LLM-enhanced SR. SSNA features three key designs to allow both efficient and effective LLM adaptation. First, SSNA learns adapters separate from LLMs, while fixing all the pre-trained parameters within LLMs to allow efficient adaptation. In addition, SSNA adapts the top-a layers of LLMs jointly, and integrates adapters sequentially for enhanced effectiveness (i.e., recommendation performance). We compare SSNA against five state-of-the-art baseline methods on five benchmark datasets using three LLMs. The experimental results demonstrate that SSNA significantly outperforms all the baseline methods in terms of recommendation performance, and achieves substantial improvement over the best-performing baseline methods at both run-time and memory efficiency during training. Our analysis shows the effectiveness of integrating adapters in a sequential manner. Our parameter study demonstrates the effectiveness of jointly adapting the top-a layers of LLMs. © 2023, CC BY.

关键词： Computational linguistics

M2: Mixed models with preferences, popularities and transitions for next-basket recommendation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Peng, Bo Ren, Zhiyun Parthasarathy, Srinivasan Ning, Xia Department of Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Department of Biomedical Informatics Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States Department of Biomedical Informatics The Ohio State University ColumbusOH43210 United States

Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions (M2) for the next-basket recommendation. This method models three important factors in next-basket generation process: 1) users' general preferences, 2) items' global popularities and 3) transition patterns among items. Unlike existing recurrent neural network-based approaches, M2does not use the complicated networks to model the transitions among items, or generate embeddings for users. Instead, it has a simple encoder-decoder based approach (ed-Trans) to better model the transition patterns among items. We compared M2with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket. Our experimental results demonstrate that M2significantly outperforms the state-of-the-art methods on all the datasets in all the tasks, with an improvement of up to 22.1%. In addition, our ablation study demonstrates that the ed-Trans is more effective than recurrent neural networks in terms of the recommendation performance. We also have a thorough discussion on various experimental protocols and evaluation metrics for the evaluation of next-basket recommendation methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks

Association between benzodiazepines use and risk of hip fracture in the elderly people: A meta-analysis of observational studies

学校读者我要写书评

暂无评论

Revue du Rhumatisme (Edition Francaise) 2020年第3期87卷 210-220页

作者： Poly, Tahmina Nasrin Islam, Md. Mohaimenul Yang, Hsuan-Chia Li, Yu-Chuan Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan International Centre for Health Information Technology (ICHIT) Taipei Medical University Taipei Taiwan Department of Dermatology Wan Fang Hospital Taipei Taiwan TMU Research Centre of Cancer Translational Medicine Taipei Medical University Taipei Taiwan Research Centre of Big Data and Meta-analysis Wan Fang Hospital Taipei Medical University Taipei Taiwan

Points essentiels•La fracture de la hanche est l’une des principales causes de handicap, de dépenses, de morbidité et de mortalité.•L’objectif principal de cette étude était d’évaluer l’ampleur du risque de fracture de la hanche sous BZD.•Le RR de fracture de la hanche était de 1,34 (IC 95 % 1,26–1,44) chez les utilisateurs de BZD par comparaison avec les non-utilisateurs.•Les médecins devraient être sensibilisés aux conséquences indésirables de la prise de BZD lorsqu’ils prescrivent ces médicaments, en particulier à des patients âgés, population au sein de laquelle les fractures de la hanche sont particulièrement prévalentes.

关键词： Fracture de la hanche Fracture Ostéoporose Benzodiazépines Anxiété Dépression

Fitness assessment in acute myeloid leukemia: recommendations from an expert panel on behalf of the European LeukemiaNet

学校读者我要写书评

暂无评论

Blood Advances 2025年第9期9卷 2207-2220页

作者： Venditti, Adriano Palmieri, Raffaele Maurillo, Luca Röllig, Christoph Wierzbowska, Agnieszka de Leeuw, David Efficace, Fabio Curti, Antonio Lam Ngai, Lok Tettero, Jesse Adès, Lionel Almeida, Antonio Bullinger, Lars Dennis, Mike Esteve, Jordi Ferrara, Felicetto Heuser, Michael Huls, Gerwin Lübbert, Michael Mehta, Priyanka Montesinos, Pau Pabst, Thomas Récher, Christian Rossi, Giuseppe Russell, Nigel Sierra, Jorge Stauder, Reinhard Vey, Norbert Walter, Roland B. Wang, Eunice Nier, Samantha Garcez Martins, Carolina Ossenkoppele, Gert Dipartimento di Biomedicina e Prevenzione Università Tor Vergata Rome Italy Department of Onco-Hematology Fondazione Policlinico Tor Vergata Rome Italy Medizinische Klinik und Poliklinik 1 Medizinische Fakultät und Universitätsklinikum Carl Gustav Carus Technische Universität Dresden Dresden Germany Department of Hematology Medical University of Lodz Lodz Poland Department of Hematology and Transplantology Provincial Multispecialized Oncology Trauma Center Lodz Poland Department of Hematology Amsterdam University Medical Center Location Vrije University Medical Center Cancer Center Amsterdam Amsterdam Netherlands Data Center and Health Outcomes Research Unit Gruppo Italiano Malattie Ematologiche Maligne dell’Adulto Rome Italy Dipartimento delle “Malattie oncologiche ed ematologiche ” Istituto di Ricovero e Cura a Carattere Scientifico Azienda Ospedaliero-Universitaria di Bologna Istituto di Ematologia “Seràgnoli” Bologna Italy Service Hématologie Séniors Hopital Saint-Louis (Assistance Publique–Hopitaux de Paris) Paris Cité University INSERM U944 Paris France Department of Hematology Hospital da Luz Lisbon Portugal and Faculdade de Medicina Universidade Católica Portuguesa Lisbon Portugal Department of Hematology Oncology and Cancer Immunology Campus Virchow Charité-Universitätsmedizin Berlin Freie Universität Berlin Humboldt-Universität Zu Berlin Germany The Christie National Health Service Foundation Trust Manchester United Kingdom Servicio de Hematología Hospital Clínic of Barcelona Institut d’Investigacions Biomèdiques August Pi i Sunyer Barcelona Spain Division of Hematology Cardarelli Hospital Naples Italy Department of Hematology Hemostasis Oncology and Stem Cell Transplantation Hannover Medical School Hannover Germany Department of Hematology University Medical Center Groningen University of Groningen Groningen Netherlands Department of Hematology Oncology and Stem Cell Transplantation Faculty of Medicine University Medical Center Freib

Fitness assessment in patients with acute myeloid leukemia (AML) is critical to deliver the right therapy to the right patient. Although several scoring systems are available to aid in determining fitness, the absence of validation studies has resulted in the lack of universally accepted assessment procedures. This limitation, combined with the increasing availability of novel agents expanding the spectrum of less-intensive options, has introduced additional complexity to the fitness assessment process. In this evolving context, fitness should reflect eligibility for a specific treatment among the several available, rather than a generic binary classification of eligibility for intensive chemotherapy. Moreover, the growing emphasis on patient-centered care, further highlights the importance of integrating quality of life, patient preferences, patient self-reported physical and social functioning status, social support, and early integration of palliative care into the assessment framework. A modern interpretation of fitness assessment should incorporate a comprehensive evaluation that extends beyond traditional clinical and biological disease characteristics. Thus, fitness assessment in patients with AML represents only 1 piece of a larger puzzle, encompassing the patient’s overall capacity to sustain and benefit from a specific therapeutic program. © 2025 American Society of Hematology.

关键词：

Bringing the Algorithms to the data - Secure Distributed Medical Analytics using the Personal Health Train (PHT-meDIC)

学校读者我要写书评

暂无评论

arXiv 2022年

作者： de Arruda Botelho Herr, Marius Graf, Michael Placzek, Peter König, Florian Bötte, Felix Stickel, Tyra Hieber, David Zimmermann, Lukas Slupina, Michael Mohr, Christopher Biergans, Stephanie Akgün, Mete Pfeifer, Nico Kohlbacher, Oliver Institute for Translational Bioinformatics University Hospital Tübingen Tübingen Germany Institute for Bioinformatics and Medical Informatics University of Tübingen Tübingen Germany Methods in Medical Informatics Department of Computer Science University of Tübingen Germany Applied Bioinformatics Department of Computer Science University of Tübingen Germany Medical Data Integration Center University Hospital Tübingen Tübingen Germany Medical Data Privacy and Privacy-Preserving ML on Healthcare Data Department of Computer Science University of Tübingen Germany

The need for data privacy and security – enforced through increasingly strict data protection regulations – renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an’algorithm to the data’ paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-source implementation of the PHT concept. Containerization allows us to easily deploy even complex data analysis pipelines (e.g, genomics, image analysis) across multiple sites in a secure and scalable manner. We discuss the underlying technological concepts, security models, and governance processes. The implementation has been successfully applied to distributed analyses of large-scale data, including applications of deep neural networks to medical image data. © 2022, CC BY.

关键词： Bioinformatics

Pacific Symposium on Biocomputing 2018

学校读者我要写书评

暂无评论

Pacific Symposium on Biocomputing

Pacific Symposium on Biocomputing 2018年 vii-ix页

作者： Altman, Russ B. Dunker, A. Keith Hunter, Lawrence Ritchie, Marylyn D. Klein, Teri E. Departments of Bioengineering Genetics Biomedical Data Science & Medicine Stanford University United States Department of Biochemistry and Molecular Biology Indiana University School of Medicine United States Department of Pharmacology University of Colorado Health Sciences Center United States Department of Biomedical and Translational Informatics Geisinger Health System United States Department of Biomedical Data Science & Medicine Stanford University United States

Bayesian geological and geophysical data fusion for the construction and uncertainty quantification of 3D geological models

学校读者我要写书评

暂无评论

Geoscience Frontiers 2021年第1期12卷 479-493页

作者： Hugo K.H.Olierook Richard Scalzo David Kohn Rohitash Chandra Ehsan Farahbakhsh Chris Clark Steven M.Reddy R.Dietmar Müller School of Earth and Planetary Sciences Curtin UniversityGPO Box U1987PerthWA6845Australia Centre for Translational Data Science University of SydneyNSW2006SydneyAustralia Sydney Informatics Hub University of SydneyNSW2006SydneyAustralia EarthByte Group School of GeosciencesUniversity of SydneyNSW2006SydneyAustralia Timescales of Mineral Systems and John de Laeter Centre Curtin UniversityGPO Box U1987PerthWA6845Australia School of Mathematics and Statistics University of New South WalesSydneyNSW2052Australia Department of Mining Engineering Amirkabir University of Technology(Tehran Polytechnic)TehranIran

Traditional approaches to develop 3D geological models employ a mix of quantitative and qualitative scientific techniques,which do not fully provide quantification of uncertainty in the constructed models and fail to optimally weight geological field observations against constraints from geophysical ***,using the Bayesian Obsidian software package,we develop a methodology to fuse lithostratigraphic field observations with aeromagnetic and gravity data to build a 3D model in a small(13.5 km×13.5 km)region of the Gascoyne Province,Western *** approach is validated by comparing 3D model results to independently-constrained geological maps and cross-sections produced by the Geological Survey of Western *** fusing geological field data with aeromagnetic and gravity surveys,we show that 89%of the modelled region has>95%certainty for a particular geological unit for the given model and *** boundaries between geological units are characterized by narrow regions with<95%certainty,which are typically 400-1000 m wide at the Earth's surface and 500-2000 m wide at ***~4 km depth,the model requires geophysical survey data with longer wavelengths(e.g.,active seismic)to constrain the deeper *** Obsidian was originally built for sedimentary basin problems,there is reasonable applicability to deformed terranes such as the Gascoyne ***,modification of the Bayesian engine to incorporate structural data will aid in developing more robust 3D ***,our results show that surface geological observations fused with geophysical survey data can yield reasonable 3D geological models with narrow uncertainty regions at the surface and shallow subsurface,which will be especially valuable for mineral exploration and the development of 3D geological models under cover.

关键词： Capricorn orogen Machine learning Bayesian inference Markov chain Monte Carlo Solid earth Mineral exploration

Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Averly, Reza Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States College of Pharmacy The Ohio State University United States

Clinical named entity recognition (NER) aims to retrieve important entities within clinical narratives. Recent works have demonstrated that large language models (LLMs) can achieve strong performance in this task. While previous works focus on proprietary LLMs, we investigate how open NER LLMs, trained specifically for entity recognition, perform in clinical NER. Our initial experiment reveals significant contrast in performance for some clinical entities and how a simple exploitment on entity types can alleviate this issue. In this paper, we introduce a novel framework, entity decomposition with filtering, or EDF. Our key idea is to decompose the entity recognition task into several retrievals of entity sub-types and then filter them. Our experimental results demonstrate the efficacies of our framework and the improvements across all metrics, models, datasets, and entity types. Our analysis also reveals substantial improvement in recognizing previously missed entities using entity decomposition. We further provide a comprehensive evaluation of our framework and an in-depth error analysis to pave future works. © 2024, CC BY.

关键词： Wiener filtering