GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference

TL;DR

This paper introduces GRMLR, a knowledge-enhanced classification model that leverages ecological knowledge graphs to improve deep-sea cold seep stage inference from very small microbial datasets, avoiding macrofauna observation at inference.

Contribution

The paper presents a novel graph-regularized multinomial logistic regression framework that incorporates ecological knowledge to improve small-data deep-sea ecological classification.

Findings

Significantly outperforms baseline models in cold seep stage inference.

Effectively constrains feature space with manifold penalty for biological consistency.

Removes macrofauna observation requirement during inference.

Abstract

Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small ($n = 13$) relative to the microbial feature dimension ($p = 26$), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment.