Papers · organized/paper_cards

论文

14 张论文卡片 · 工程化 · 综述

开放获取 全部 绿色 · 677
条目 E-NF2:MLOps 架构指南 — 25 条模型集成/部署规范(灰色文献综述)
arXiv:2606.06535 工程化 综述 OA · 绿色 被引 0 · S2 + OpenAlex

本文贡献了一组在架构层面具有重要意义的 MLOps 集成与部署指南(共 25 条),分为五类,并阐述其对整体系统架构的影响。This work contributes a collection of 25 architecturally significant MLOps guidelines for model integration and deployment, organized into five categories, and describes their impact on the overall system architecture.

⑤ MLOps系统综述(arXiv:2604.16371)
⑤ MLOps系统综述(arXiv:2604.16371)
arXiv:2604.16371 工程化 综述 OA · 绿色 被引 2 · S2

对聚焦MLOps工具的学术文献进行系统综述,揭示其功能、范围及其旨在解决的挑战,并突出真实MLOps pipeline中各工具间互操作性的重要性。A systematic review of the academic literature focused on MLOps tools is conducted to reveal their function, scope, and the challenges they are designed to address and highlight the importance of interoperability across MLOps tools in real-world MLOps pipelines.

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
增强 ChatGPT 提示工程的提示模式目录
arXiv:2302.11382 工程化 综述 OA · 绿色 被引 1884 · S2

本文描述了一份以模式形式呈现的 prompt 工程技巧目录,这些技巧已被用于解决与 LLMs 对话时的常见问题,以改进 LLM 对话的输出。A catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs to improve the outputs of LLM conversations is described.

A Comprehensive Survey on Transfer Learning
迁移学习全面综述
arXiv:1911.02685 工程化 综述 OA · 绿色 被引 6058 · S2

本综述尝试连接并系统化现有迁移学习研究,全面总结与阐释迁移学习的机制与策略,帮助读者更好地理解当前研究现状与思路。This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas.

A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
预训练基础模型全面综述:从 BERT 到 ChatGPT 的发展历程
arXiv:2302.09419 工程化 综述 OA · 绿色 被引 750 · S2

本综述旨在阐明 PFMs 在可扩展性、安全性、逻辑推理能力、跨领域学习能力以及面向 AGI 的友好交互能力方面的研究。This survey aims to shed light on the research of the PFMs on scalability, security, logical reasoning ability, cross-domain learning ability, and the user-friendly interactive ability for artificial general intelligence.

A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective
面向机器学习的数据采集综述:大数据–AI 融合视角
arXiv:1811.03402 工程化 综述 OA · 绿色 被引 825 · S2

本综述从数据管理视角对数据收集进行全面研究,提供了相关操作的研究全景图、何时使用何种技术的指导原则,并识别出值得关注的研究挑战。This survey performs a comprehensive study of data collection from a data management point of view, providing a research landscape of these operations, guidelines on which technique to use when, and identify interesting research challenges.

Federated Learning in Mobile Edge Networks: A Comprehensive Survey
移动边缘网络中的联邦学习:全面综述
arXiv:1909.11875 工程化 综述 OA · 绿色 被引 2355 · S2

在大规模复杂的移动边缘网络中,涉及具有不同约束的异构设备,这为大规模 FL 实施带来了通信成本、资源分配以及隐私安全方面的挑战。In a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved, this raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale.

Online Learning: A Comprehensive Survey
在线学习全面综述
arXiv:1802.02871 工程化 综述 OA · 绿色 被引 851 · S2

本综述旨在通过对基本思想与关键原则的系统回顾以及对不同算法与技术的合理分类,提供在线机器学习文献的全面综述。This survey aims to provide a comprehensive survey of the online machine learning literatures through a systematic review of basic ideas and key principles and a proper categorization of different algorithms and techniques.

Graph Neural Networks: A Review of Methods and Applications
图神经网络:方法与应用综述
arXiv:1812.08434 工程化 综述 OA · 绿色 被引 7272 · S2

对现有图神经网络模型进行了详细综述,系统性地归纳了其应用,并提出了四个有待解决的未来研究方向A detailed review over existing graph neural network models is provided, systematically categorize the applications, and four open problems for future research are proposed.

Generalizing from a Few Examples: A Survey on Few-Shot Learning
基于少量样本的泛化:小样本学习综述
arXiv:1904.05046 工程化 综述 OA · 绿色 被引 2185 · S2

一篇全面综述,旨在深入理解 Few-shot Learning,并从三个维度对 FSL 方法进行分类:数据层面——利用先验知识扩充监督经验;模型层面——利用先验知识缩小假设空间规模;算法层面——利用先验知识改变在给定假设空间中对最优假设的搜索方式A thorough survey to fully understand Few-shot Learning and categorize FSL methods from three perspectives: data, which uses prior knowledge to augment the supervised experience; model, which uses prior knowledge to reduce the size of the hypothesis space; and algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space.

A Survey on Metric Learning for Feature Vectors and Structured Data
面向特征向量与结构化数据的度量学习综述
arXiv:1306.6709 工程化 综述 OA · 绿色 被引 719 · S2

本文对度量学习文献进行了系统综述,阐述了每种方法的优缺点,并介绍了近期涌现的一系列强大替代方法,包括非线性度量学习、相似性学习与局部度量学习。A systematic review of the metric learning literature is proposed, highlighting the pros and cons of each approach and presenting a wide range of methods that have recently emerged as powerful alternatives, including nonlinear metric learning, similarity learning and local metric learning.

A Survey on Multi-Task Learning
多任务学习综述
arXiv:1707.08114 工程化 综述 OA · 绿色 被引 3073 · S2

从算法建模、应用和理论分析角度对 MTL 的综述,给出了 MTL 的定义,并将不同 MTL 算法分为五类:特征学习方法、低秩方法、任务聚类方法、任务关系学习方法和分解方法A survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses, which gives a definition of MTL and classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach,task relation learning approach and decomposition approach.

A Brief Review of Nature-Inspired Algorithms for Optimization
仿生优化算法简要综述
arXiv:1307.4186 工程化 综述 OA · 绿色 被引 676 · S2

较为全面地列举了基于群体智能、生物启发、物理启发和化学启发(按灵感来源分类)的所有算法,这些算法已成为解决实际问题的流行工具A relatively comprehensive list of all the algorithms based on swarm intelligence, bio-inspired, physics-based and chemistry-based, depending on the sources of inspiration, that have become popular tools for solving real-world problems.

Paper Cards Index
论文卡片索引
工程化 综述