Scale-Free Graph-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jianglin, Liu, Yixuan, Zhang, Yitian, Fu, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917931930091520
author Lu, Jianglin
Liu, Yixuan
Zhang, Yitian
Fu, Yun
author_facet Lu, Jianglin
Liu, Yixuan
Zhang, Yitian
Fu, Yun
contents Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning. A typical GLM consists of two key stages: graph generation and text embedding, which are usually implemented by inferring a latent graph and finetuning a language model (LM), respectively. However, the former often relies on artificial assumptions about the underlying edge distribution, while the latter requires extensive data annotations. To tackle these challenges, this paper introduces a novel GLM that integrates graph generation and text embedding within a unified framework. Specifically, for graph generation, we leverage an inherent characteristic of real edge distribution--the scale-free property--as a structural prior. We unexpectedly find that this natural property can be effectively approximated by a simple k-nearest neighbor (KNN) graph. For text embedding, we develop a graph-based pseudo-labeler that utilizes scale-free graphs to provide complementary supervision for improved LM finetuning. Extensive experiments on representative datasets validate our findings on the scale-free structural approximation of KNN graphs and demonstrate the effectiveness of integrating graph generation and text embedding with a real structural prior. Our code is available at https://github.com/Jianglin954/SFGL.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scale-Free Graph-Language Models
Lu, Jianglin
Liu, Yixuan
Zhang, Yitian
Fu, Yun
Computation and Language
Artificial Intelligence
Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning. A typical GLM consists of two key stages: graph generation and text embedding, which are usually implemented by inferring a latent graph and finetuning a language model (LM), respectively. However, the former often relies on artificial assumptions about the underlying edge distribution, while the latter requires extensive data annotations. To tackle these challenges, this paper introduces a novel GLM that integrates graph generation and text embedding within a unified framework. Specifically, for graph generation, we leverage an inherent characteristic of real edge distribution--the scale-free property--as a structural prior. We unexpectedly find that this natural property can be effectively approximated by a simple k-nearest neighbor (KNN) graph. For text embedding, we develop a graph-based pseudo-labeler that utilizes scale-free graphs to provide complementary supervision for improved LM finetuning. Extensive experiments on representative datasets validate our findings on the scale-free structural approximation of KNN graphs and demonstrate the effectiveness of integrating graph generation and text embedding with a real structural prior. Our code is available at https://github.com/Jianglin954/SFGL.
title Scale-Free Graph-Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.15189