Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss

TL;DR

This paper introduces a supervised contrastive loss that incorporates taxonomic hierarchy relationships, improving representation learning by capturing semantic structures beyond class labels, with applications in medical and noise-based datasets.

Contribution

It proposes a novel contrastive loss that explicitly integrates taxonomic hierarchy information, enhancing semantic representation learning.

Findings

Outperforms standard supervised contrastive loss by leveraging hierarchy information.

Achieves up to 7% performance improvement in medical and noise-based datasets.

Demonstrates flexibility of taxonomy integration across different domains.

Abstract

In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervised contrastive loss operates by enforcing that images with the same class label (positive samples) project closer to each other than images with differing class labels (negative samples). The advantage of this approach is that it directly penalizes the structure of the representation space itself. This enables greater flexibility with respect to encoding semantic concepts. However, the standard supervised contrastive loss only enforces semantic structure based on the downstream task (i.e. the class label). In reality, the class label is only one level of a \emph{hierarchy of different semantic relationships known as a taxonomy}. For example, the class label is oftentimes the species of an animal, but between different classes there are higher order relationships such as all animals with wings being ``birds". We show that by explicitly accounting for these relationships with a weighting penalty in the contrastive loss we can out-perform the supervised contrastive loss. Additionally, we demonstrate the adaptability of the notion of a taxonomy by integrating our loss into medical and noise-based settings that show performance improvements by as much as 7%.