Nonstationary Distance Metric Learning
This addresses the challenge of adapting distance metrics over time for improved retrieval, classification, and clustering in dynamic environments, representing an incremental advance in online metric learning.
The paper tackles the problem of learning distance metric transformations when the underlying constraint generation process is nonstationary, due to changes in clustering or feature subspaces, and proposes COMID-SADL, an adaptive online approach that shows significant performance improvements over previous batch and online algorithms.
Recent work in distance metric learning has focused on learning transformations of data that best align with provided sets of pairwise similarity and dissimilarity constraints. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the better adapted distance or similarity measures. Here, we introduce 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 to the feature subspaces in which the class structure is apparent. We propose and evaluate COMID-SADL, an 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 demonstrate COMID-SADL on both real and synthetic data sets and show significant performance improvements relative to previously proposed batch and online distance metric learning algorithms.