Quadruplet Loss is a loss function used during the training of a model, aiming to learn embeddings (vector representations) in a way that pulls the embeddings of the anchor and positive closer together while pushing the embeddings of the anchor and negatives farther apart. A quadruplet refers to a set of four samples, typically organized into pairs of anchor-positive samples (similar to the anchor) and anchor-negative samples (dissimilar to the anchor). The loss function encourages a desirable margin between positive and negative pairs.


Ordinal Quadruplet: Retrieval of Missing Labels in Ordinal Time Series

In this paper, we propose an ordered time series classification framework that is robust against missing classes in the training data, i.e., during testing we can prescribe classes that are missing during training. This framework relies on two main components: (1) our newly proposed ordinal quadruplet loss, which forces the model to learn latent representation while preserving the ordinal relation among labels, (2) testing procedure, which utilizes the property of latent representation (order preservation). We conduct experiments based on real world multivariate time series data and show the significant improvement in the prediction of missing labels even with 40% of the classes are missing from training. Compared with the well known triplet loss optimization augmented with interpolation for missing information, in some cases, we nearly double the accuracy.