Hyperbolic Multimodal Representation Learning for Biological Taxonomies

TL;DR

This paper explores hyperbolic neural networks for embedding multimodal biological data into hierarchical taxonomies, demonstrating improved performance in species classification tasks, especially for unseen species using DNA barcodes.

Contribution

It introduces a novel hyperbolic embedding framework with a stacked entailment objective for multimodal biological data, enhancing hierarchical taxonomic modeling.

Findings

Hyperbolic embeddings outperform Euclidean baselines on unseen species classification.

The method achieves competitive results on the BIOSCAN-1M dataset.

Fine-grained classification and open-world generalization remain challenging.

Abstract

Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We investigate whether hyperbolic networks can provide a better embedding space for such hierarchical models. Our method embeds multimodal inputs into a shared hyperbolic space using contrastive and a novel stacked entailment-based objective. Experiments on the BIOSCAN-1M dataset show that hyperbolic embedding achieves competitive performance with Euclidean baselines, and outperforms all other models on unseen species classification using DNA barcodes. However, fine-grained classification and open-world generalization remain challenging. Our framework offers a structure-aware foundation for biodiversity modelling, with potential applications to species discovery, ecological monitoring, and conservation efforts.