Learning Meta-Distance for Sequences by Learning a Ground Metric via Virtual Sequence Regression
Learning Meta-Distance for Sequences by Learning a Ground Metric via Virtual Sequence Regression
复制标题
通过虚拟序列回归学习基本度量来学习序列的元距离
DOI：
10.1109/tpami.2020.3010568
复制
发表时间：
2022
影响因子：
23.6
通讯作者：
Wu, Ying
中科院分区：
文献类型：
--
作者：
Su, Bing;Wu, Ying
序列之间的距离本质上是结构性的，因为它需要在具有不同长度的序列中建立时间相关向量之间的时间比对。通常，序列的距离严重依赖于序列中的向量之间的基础度量来推断比对，因此可以被视为基础度量上的元距离。从多维序列中学习这样的元距离是有吸引力的，但具有挑战性。我们建议通过学习序列中向量的基础度量来学习元距离。学习样本是向量的序列，其中向量之间的基础度量如何引起元距离。目标是由学习的基础度量引起的元距离对于来自不同类的序列产生大的值，并且对于来自相同类的序列产生小的值。我们制定的地面度量作为一个参数的元距离和回归每个序列相关联的预生成的虚拟序列w.r.t.元距离，其中用于不同类别的序列的虚拟序列被很好地分离。我们开发了一般的迭代解决方案来学习Mahalanobis度量和神经网络诱导的深度度量，用于任何基于地面度量的序列距离。在多个序列数据集上的实验表明了所提方法的有效性和效率。
Distance between sequences is structural by nature because it needs to establish the temporal alignments among the temporally correlated vectors in sequences with varying lengths. Generally, distances for sequences heavily depend on the ground metric between the vectors in sequences to infer the alignments and hence can be viewed as meta-distances upon the ground metric. Learning such meta-distance from multi-dimensional sequences is appealing but challenging. We propose to learn the meta-distance through learning a ground metric for the vectors in sequences. The learning samples are sequences of vectors for which how the ground metric between vectors induces the meta-distance is given. The objective is that the meta-distance induced by the learned ground metric produces large values for sequences from different classes and small values for those from the same class. We formulate the ground metric as a parameter of the meta-distance and regress each sequence to an associated pre-generated virtual sequence w.r.t. the meta-distance, where the virtual sequences for sequences of different classes are well-separated. We develop general iterative solutions to learn both the Mahalanobis metric and the deep metric induced by a neural network for any ground-metric-based sequence distance. Experiments on several sequence datasets demonstrate the effectiveness and efficiency of the proposed methods.