.png){kind=icon}
返回
Self-supervised Metric Learning in Multi-View Data: A Downstream Task Perspective
.png){kind=icon}
OA
AI
DOI：10.1080/01621459.2022.2057317.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Self-supervised metric learning has been a successful approach for learning a distance from an unlabeled dataset. The resulting distance is broadly useful for improving various distance-based downstream tasks, even when no information from downstream tasks is used in the metric learning stage. To gain insights into this approach, we develop a statistical framework to theoretically study how self-supervised metric learning can benefit downstream tasks in the context of multi-view data. Under this framework, we show that the target distance of metric learning satisfies several desired properties for the downstream tasks. On the other hand, our investigation suggests the target distance can be further improved by moderating each direction's weights. In addition, our analysis precisely characterizes the improvement by self-supervised metric learning on four commonly used downstream tasks: sample identification, two-sample testing, k-means clustering, and k-nearest neighbor classification. When the distance is estimated from an unlabeled dataset, we establish the upper bound on distance estimation's accuracy and the number of samples sufficient for downstream task improvement. Finally, numerical experiments are presented to support the theoretical results in the article. Supplementary materials for this article are available online.
Keyword:
k-means
k-nearest neighbor
Metric learning
Two-sample testing
期刊
J
IF:
3
论文数:
5.2K
被引数:
4.8W
机构
引用论文
分享收藏EQUIVALENCE OF DISTANCE-BASED AND RKHS-BASED STATISTICS IN HYPOTHESIS TESTING.png)
ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏Fast generalization rates for distance metric learning: Improved theoretical analysis for smooth strongly convex distance metric learningMACHINE LEARNINGOAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏
查看更多内容