arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09140cs.LGstat.ML
收藏

元邻域

Meta-Neighborhoods

University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Department of Computer Science(计算机科学系)

Siyuan Shan, Yang Li, Junier Oliva

摘要:

基于输入进行自适应预测是一般人工智能的一项重要能力。在这项工作中,我们在这个方向上前进,并提出了一个半参数的方法,元邻域,预测是自适应的输入的邻域。我们表明,元邻域是一个推广的$k$最近的邻居。由于局部邻域周围的流形结构更简单,元邻域更准确地表示预测分布$p(y \mid x)$。为了减少内存和计算开销,我们提出了诱导邻域,总结训练数据到一个更小的字典。然后利用基于元学习的训练机制来共同学习诱导邻域和模型。大量的研究表明,我们的方法的优越性。

英文摘要:

Making an adaptive prediction based on one's input is an important ability for general artificial intelligence. In this work, we step forward in this direction and propose a semi-parametric method, Meta-Neighborhoods, where predictions are made adaptively to the neighborhood of the input. We show that Meta-Neighborhoods is a generalization of $k$-nearest-neighbors. Due to the simpler manifold structure around a local neighborhood, Meta-Neighborhoods represent the predictive distribution $p(y \mid x)$ more accurately. To reduce memory and computation overhead, we propose induced neighborhoods that summarize the training data into a much smaller dictionary. A meta-learning based training mechanism is then exploited to jointly learn the induced neighborhoods and the model. Extensive studies demonstrate the superiority of our method.

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。

↑