\textsc{Text2Graph}: Combining Lightweight LLMs and GNNs for Efficient Text Classification in Label-Scarce Scenarios
This work addresses the sustainability and efficiency challenges of using LLMs for large-scale text classification in high-performance computing environments, though it is incremental as it builds on existing text-to-graph approaches.
The paper tackled the problem of high computational and environmental costs of large language models (LLMs) for text classification in label-scarce scenarios by introducing Text2Graph, a modular framework combining LLM-based partial annotation with graph neural network (GNN) label propagation, achieving competitive results with significantly reduced energy consumption and carbon emissions.
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 \textsc{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 \textsc{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.