STAGE: Simplified Text-Attributed Graph Embeddings Using Pre-trained LLMs

TL;DR

STAGE introduces a simple method that uses pre-trained LLMs to generate node feature embeddings for text-attributed graphs, achieving competitive results with less complexity than current state-of-the-art methods.

Contribution

The paper proposes a straightforward approach leveraging pre-trained LLMs for node feature generation in GNNs, simplifying the pipeline while maintaining strong performance.

Findings

Achieves competitive node classification results on benchmarks.

Simplifies the embedding process compared to existing methods.

Scales to larger graphs using diffusion-pattern GNNs.

Abstract

We present Simplified Text-Attributed Graph Embeddings (STAGE), a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages Large-Language Models (LLMs) to generate embeddings for textual attributes. STAGE achieves competitive results on various node classification benchmarks while also maintaining a simplicity in implementation relative to current state-of-the-art (SoTA) techniques. We show that utilizing pre-trained LLMs as embedding generators provides robust features for ensemble GNN training, enabling pipelines that are simpler than current SoTA approaches which require multiple expensive training and prompting stages. We also implement diffusion-pattern GNNs in an effort to make this pipeline scalable to graphs beyond academic benchmarks.