Text2Graph: Combining Lightweight LLMs and GNNs for Efficient Text Classification in Label-Scarce Scenarios

TL;DR

Text2Graph is a modular framework combining lightweight LLMs and GNNs for efficient, sustainable zero-shot text classification, achieving competitive results with lower energy consumption.

Contribution

We introduce Text2Graph, a flexible open-source framework that integrates LLMs and GNNs for zero-shot text classification, emphasizing sustainability and ease of component customization.

Findings

Graph-based propagation achieves competitive accuracy.

Significant reduction in energy consumption and carbon emissions.

Framework supports flexible combination of models and methods.

Abstract

Large Language Models (LLMs) have become effective zero-shot classifiers, but their high computational requirements and environmental costs limit their practicality for large-scale annotation in high-performance computing (HPC) environments. To support more sustainable workflows, we present Text2Graph, an open-source Python package that provides a modular implementation of existing text-to-graph classification approaches. The framework enables users to combine LLM-based partial annotation with Graph Neural Network (GNN) label propagation in a flexible manner, making it straightforward to swap components such as feature extractors, edge construction methods, and sampling strategies. We benchmark Text2Graph on a zero-shot setting using five datasets spanning topic classification and sentiment analysis tasks, comparing multiple variants against other zero-shot approaches for text classification. In addition to reporting performance, we provide detailed estimates of energy consumption and carbon emissions, showing that graph-based propagation achieves competitive results at a fraction of the energy and environmental cost.