English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, there have been remarkable advancements in nodeclassification achieved by Graph Neural Networks (GNNs). However, theynecessitate abundant high-quality labels to ensure promising performance. Incontrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiencyon text-attributed graphs. Yet, they face challenges in efficiently processingstructural data and suffer from high inference costs. In light of theseobservations, this work introduces a label-free node classification on graphswith LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMswhile mitigating their limitations. Specifically, LLMs are leveraged toannotate a small portion of nodes and then GNNs are trained on LLMs'annotations to make predictions for the remaining large portion of nodes. Theimplementation of LLM-GNN faces a unique challenge: how can we actively selectnodes for LLMs to annotate and consequently enhance the GNN training? How canwe leverage LLMs to obtain annotations of high quality, representativeness, anddiversity, thereby enhancing GNN performance with less cost? To tackle thischallenge, we develop an annotation quality heuristic and leverage theconfidence scores derived from LLMs to advanced node selection. Comprehensiveexperimental results validate the effectiveness of LLM-GNN. In particular,LLM-GNN can achieve an accuracy of 74.9% on a vast-scale dataset \products witha cost less than 1 dollar.

Label-free Node Classification on Graphs with Large Language Models (LLMS)