Estimating Posterior Ratio for Classification: Transfer Learning from Probabilistic Perspective
Estimating Posterior Ratio for Classification: Transfer Learning from Probabilistic Perspective
复制标题
DOI：
10.1137/1.9781611974348.84
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Song Liu;K. Fukumizu
中科院分区：
文献类型：
--
作者：
Song Liu;K. Fukumizu
迁移学习假设相似任务的分类器共享某些参数结构。不幸的是，现代分类器使用复杂的特征表示与巨大的参数空间，导致昂贵的转移。在从一个分类器到另一个分类器的变化应该是“简单”的印象下，本文提出了一种只学习“差异”的有效迁移学习标准。我们训练了一个后验比，它可以最大限度地减少目标学习风险的上限。后验比模型完全不需要与源分类器共享相同的参数空间，因此它可以很容易地建模和有效地训练。因此，通过简单地将现有的概率分类器与学习的后验比相乘来获得所得到的分类器。
Transfer learning assumes classifiers of similar tasks share certain parameter structures. Unfortunately, modern classifiers uses sophisticated feature representations with huge parameter spaces which lead to costly transfer. Under the impression that changes from one classifier to another should be ``simple'', an efficient transfer learning criteria that only learns the ``differences'' is proposed in this paper. We train a \emph{posterior ratio} which turns out to minimizes the upper-bound of the target learning risk. The model of posterior ratio does not have to share the same parameter space with the source classifier at all so it can be easily modelled and efficiently trained. The resulting classifier therefore is obtained by simply multiplying the existing probabilistic-classifier with the learned posterior ratio.