Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the better adapted distance or similarity measures. Here, we address the problem of learning these transformations when the underlying constraint generation process is nonstationary. This nonstationarity can be due to changes in either the ground-truth clustering used to generate constraints or changes in the feature subspaces in which the class structure is apparent. We propose Online Convex Ensemble StrongLy Adaptive Dynamic Learning (OCELAD), a general adaptive, online approach for learning and tracking optimal metrics as they change over time that is highly robust to a variety of nonstationary behaviors in the changing metric. We apply the OCELAD framework to an ensemble of online learners. Specifically, we create a retro-initialized composite objective mirror descent (COMID) ensemble (RICE) consisting of a set of parallel COMID learners with different learning rates, and demonstrate parameter-free RICE-OCELAD metric learning on both synthetic data and a highly nonstationary Twitter dataset. We show significant performance improvements and increased robustness to nonstationary effects relative to previously proposed batch and online distance metric learning algorithms.
Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
The University of Sydney（悉尼大学）；Hong Kong Baptist University（香港浸会大学）；The University of Melbourne（墨尔本大学）；Xidian University（西安电子科技大学）；Brain-Inspired Technology Co., Ltd.（脑启发技术有限公司）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
Telecom ParisTech（巴黎高等电信学院）；Université Paris Saclay（巴黎萨克雷大学）；IDEMIA（艾德米亚）
在许多情况下，在特征空间上选择适当的相似性度量或度量极大地决定了机器学习方法的性能。自动构建这样的度量是度量/相似性学习的特定目的。在Vogel et al.（2018）中，相似性学习被公式化为成对二分排序问题：理想情况下，特征空间中的两个观测值属于同一类（或共享相同标签）的概率越大，它们之间的相似性度量就越高。从这个角度来看，ROC曲线是一个合适的性能标准，本文的目标是扩展基于递归树的ROC优化技术，以提出高效的相似性学习算法。这种迭代划分程序在成对设置的有效性建立的U-过程的理论和从一个实用的角度，它是在长度上讨论如何实现它们的分裂规则专门为相似性学习任务。除了这些理论/方法的贡献，数值实验显示，并提供了强有力的经验证据，我们提出的算法方法的性能。
GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
University of Oxford（牛津大学）；Amazon Web Services AI Shanghai Lablet（亚马逊云科技AI上海实验室）；The Alan Turing Institute（阿兰·图灵研究所）；Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks
Beihang University（北京航空航天大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Lehigh University（理海大学）
