Efficient Robust Optimal Transport with Application to Multi-Label Classification

被引:2
作者
Jawanpuria, Pratik [1 ]
Satyadev, N. T., V [2 ]
Mishra, Bamdev [1 ]
机构
[1] Microsoft, Hyderabad, India
[2] Vayve Technol, Mumbai, Maharashtra, India
来源
2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC) | 2021年
关键词
D O I
10.1109/CDC45484.2021.9683259
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Optimal transport (OT) is a powerful geometric tool for comparing two distributions and has been employed in various machine learning applications. In this work, we propose a novel OT formulation that takes feature correlations into account while learning the transport plan between two distributions. We model the feature-feature relationship via a symmetric positive semi-definite Mahalanobis metric in the OT cost function. For a certain class of regularizers on the metric, we show that the optimization strategy can be considerably simplified by exploiting the problem structure. For high-dimensional data, we additionally propose suitable low-dimensional modeling of the Mahalanobis metric. Overall, we view the resulting optimization problem as a non-linear OT problem, which we solve using the Frank-Wolfe algorithm. Empirical results on the discriminative learning setting, such as tag prediction and multi-class classification, illustrate the good performance of our approach.
引用
收藏
页码:1490 / 1495
页数:6
相关论文
共 26 条
  • [1] Bojanowski P., 2017, T ASSOC COMPUT LING, V5, P135, DOI [10.1162/tacl_a_00051, DOI 10.1162/TACLA00051]
  • [2] Optimal Transport for Domain Adaptation
    Courty, Nicolas
    Flamary, Remi
    Tuia, Devis
    Rakotomamonjy, Alain
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (09) : 1853 - 1865
  • [3] Cuturi M., 2013, Advances in neural information processing systems, P2292, DOI DOI 10.48550/ARXIV.1306.0895
  • [4] Dhouib S., 2020, ICML
  • [5] Douik A., 2018, ICML
  • [6] Frogner C, 2015, ADV NEUR IN, V28
  • [7] Genevay Aude, 2018, AISTATS
  • [8] Gurumoorthy K., 2021, ECML
  • [9] Jaggi Martin, 2013, INT C MACH LEARN
  • [10] Jawanpuria P., 2020, ARXIV201011852