Adaptive von Mises-Fisher Likelihood Loss for Supervised Deep Time Series Hashing
This work addresses indexing efficiency for time series data mining, but it is incremental as it builds on existing deep hashing methods with a novel loss function.
The paper tackles the problem of information loss in supervised deep hashing for time series indexing by proposing a von Mises-Fisher hashing loss that maps data to a hyperspherical space, and experimental results show it outperforms existing baselines.
Indexing time series by creating compact binary representations is a fundamental task in time series data mining. Recently, deep learning-based hashing methods have proven effective for indexing time series based on semantic meaning rather than just raw similarity. The purpose of deep hashing is to map samples with the same semantic meaning to identical binary hash codes, enabling more efficient search and retrieval. Unlike other supervised representation learning methods, supervised deep hashing requires a discretization step to convert real-valued representations into binary codes, but this can induce significant information loss. In this paper, we propose a von Mises-Fisher (vMF) hashing loss. The proposed deep hashing model maps data to an M-dimensional hyperspherical space to effectively reduce information loss and models each data class as points following distinct vMF distributions. The designed loss aims to maximize the separation between each modeled vMF distribution to provide a better way to maximize the margin between each semantically different data sample. Experimental results show that our method outperforms existing baselines. The implementation is publicly available at https://github.com/jmpq97/vmf-hashing