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

2026-03-25

AI Summary

This study addresses the challenge of inferring deep-sea cold seep successional stages, which is hindered by the high operational costs of manned submersibles and extremely limited microbial samples (n=13, p=26), leading to severe overfitting in data-driven models. To overcome this, we propose the first few-shot classification framework that integrates an ecological knowledge graph, leveraging macrofauna–microbiota coupling relationships and microbial co-occurrence networks to construct structural priors that guide stage inference based solely on microbial abundances. Our method employs graph-regularized multinomial logistic regression (GRMLR) with manifold penalties, incorporating macro–micro associations during training while requiring no macrofaunal observations at inference time, thereby ensuring biologically consistent and robust classification. Experiments demonstrate that our approach significantly outperforms standard baselines, achieving both interpretability and scalability even under extreme data scarcity.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• small-data learning
• deep-sea cold seep
• microbial communities
• overfitting
• stage inference

Innovation

• knowledge-enhanced learning
• graph-regularized logistic regression
• small-data classification
• microbial community analysis
• ecological knowledge graph