Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Survival Tree01:19

Survival Tree

514
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
514

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Build fair machine learning models to predict adverse outcomes for heart failure patients with preserved ejection fraction and with reduced ejection fraction.

JAMIA open·2026
Same author

KAT2A-IGF2BP1-CXCL2 axis in the high lactate tumor microenvironment facilitates resistance to anti-PD-1 therapy in lung adenocarcinoma by recruiting myeloid-derived suppressor cells.

Cell death & disease·2026
Same author

Knowledge Graph Augmented Large Language Models for Disease Prediction.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Why Empirical Risk Minimization Performs Well for Open Set Domain Adaptation: A Theoretical Analysis From Causal View.

IEEE transactions on neural networks and learning systems·2026

相关实验视频

Updated: May 6, 2026

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

9.9K

什么时候预训练图形神经网络? 从数据生成的角度来看!

Yuxuan Cao1, Jiarong Xu2, Carl Yang3

  • 1Zhejiang University, Fudan University.

KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
|February 9, 2024
PubMed
概括

本研究介绍了W2PGNN,这是一个框架来确定何时图表预训练是有益的,解决负面转移问题. 它通过分析数据集之间的生成机制来量化培训前的可行性.

关键词:
图形神经网络的神经网络图表预先培训的培训.

更多相关视频

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.1K

相关实验视频

Last Updated: May 6, 2026

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

9.9K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.1K

科学领域:

  • 图形表示学习学习学习图形表示.
  • 机器学习理论机器学习理论

背景情况:

  • 图表预培训旨在从未标记的数据中转移知识,以改进下游任务.
  • 负转移仍然是一个重大挑战,限制了当前图形预训练方法的有效性.
  • 现有的研究集中在"什么"和"如何"进行预培训,但忽视了"什么时候"预培训是有利的.

研究的目的:

  • 引入一个通用框架,W2PGNN,确定应用图形预训练的最佳情况.
  • 在进行计算密集的预训练或微调之前,解决"何时进行预训练"这一关键问题.
  • 探索连接培训前和下游数据的生成机制.

主要方法:

  • W2PGNN将预训练数据合并到图形基中,识别基本的可转移模式.
  • 它使用图形基的凸形组合定义了一个生成器空间.
  • 预训练的可行性是通过从这个空间生成下游数据的概率来量化.

主要成果:

  • W2PGNN提供了一个理论上可靠的方法来定义图形预训练模型的应用范围.
  • 经验证据支持其量化培训前可行性和指导培训前数据选择的能力.
  • 该框架有助于确定图形预训练产生明显益处的场景,减轻负面转移.

结论:

  • W2PGNN提供了一种新的方法来评估图表预训练的实用性,超越"什么"和"如何"到"何时".
  • 该框架使得在应用图形预训练模型时能够做出明智的决策,从而提高下游任务性能.
  • 它提供了一种原则性的方法来避免负转移,并最大限度地发挥图形预训练的好处.