集体分类和半监督学习有什么区别
What's the difference between collective classification and semi-supervised learning
我遇到了如题的烦恼：
集体分类的定义是"Collective classification is the area in machine learning, in which unknown nodes in the network are classified based on the classes assigned to the known nodes and the network structure only."
半监督学习是为给定的未标记数据推断出正确的标签---wiki
因此它们之间的唯一区别是 cc 有分类而 ssl 没有。对吗？
半监督学习更通用——它不specify/stipulate输入数据的结构。可以概括为"learning from a combination of labeled and unlabeled data points"。 执行推理的方法 也未指定。
"Collective classification" 正如您在上面反映的 确实 指定了推断未标记点的方式：
based on the classes assigned to the known nodes and the network
structure only.
所以对他们的数据有额外的期望
- 以图形结构表示
- 它们的相关性可用于计算它们的相对相似性，从而计算它们的 class
本文https://www.cs.uic.edu/~xkong/sdm11_icml.pdf对集体分类的总结有助于说明对数据结构和语义的（更高）期望：
Collective classification in relational data has become animportant and
active research topic in the last decade,where class labels for a
group of linked instances are cor-related and need to be predicted
simultaneously.
关于类型适用问题的注释也很有启发性——注意它们是面向图形的数据分析任务：
Collective classification has a wide variety of real
world appli-cations,e.g.hyperlinked document classification,
socialnetworks analysis and collaboration networks analysis
我遇到了如题的烦恼： 集体分类的定义是"Collective classification is the area in machine learning, in which unknown nodes in the network are classified based on the classes assigned to the known nodes and the network structure only." 半监督学习是为给定的未标记数据推断出正确的标签---wiki
因此它们之间的唯一区别是 cc 有分类而 ssl 没有。对吗？
半监督学习更通用——它不specify/stipulate输入数据的结构。可以概括为"learning from a combination of labeled and unlabeled data points"。 执行推理的方法 也未指定。
"Collective classification" 正如您在上面反映的 确实 指定了推断未标记点的方式：
based on the classes assigned to the known nodes and the network structure only.
所以对他们的数据有额外的期望 - 以图形结构表示 - 它们的相关性可用于计算它们的相对相似性，从而计算它们的 class
本文https://www.cs.uic.edu/~xkong/sdm11_icml.pdf对集体分类的总结有助于说明对数据结构和语义的（更高）期望：
Collective classification in relational data has become animportant and active research topic in the last decade,where class labels for a group of linked instances are cor-related and need to be predicted simultaneously.
关于类型适用问题的注释也很有启发性——注意它们是面向图形的数据分析任务：
Collective classification has a wide variety of real world appli-cations,e.g.hyperlinked document classification, socialnetworks analysis and collaboration networks analysis