arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.07342cs.SIcs.LG
收藏

用于网络函数学习的采样

Sampling for network function learning

Li-Chun Zhang

摘要:

给定一个有值图,其中图的节点和边都与一个或多个值相关联,对于给定节点的任何网络函数都必须根据该节点及其在图中的连接节点来定义。一般来说,将相同的定义应用于整个图或其任何给定的子图将导致系统不同的网络函数。本文研究了图抽样方法用于网络函数学习的可行性,以及基于样本图的网络函数学习方法。这在边未知无法开始或图太大(或动态)而无法完全处理时非常有用。

英文摘要:

Given a valued graph, where both the nodes and the edges of the graph are associated with one or several values, any network function for a given node must be defined in terms of that node and its connected nodes in the graph. Generally, applying the same definition to the whole graph or any given subgraph of it would result in systematically different network functions. In this paper we consider the feasibility of graph sampling approach to network function learning, as well as the corresponding learning methods based on the sample graphs. This can be useful either when the edges are unknown to start with or the graph is too large (or dynamic) to be processed entirely.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑