AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding

Yanchao Tan, Zihao Zhou, Hang Lv, Weiming Liu, Carl Yang

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add graph-aware fine-tuning on random-walk text to the plain LM (DRoBERTa) (ablation)LM (DRoBERTa) · PubMed link predictionAUC: 60.97 -> 85.65Improved
add graph-aware fine-tuning to the plain LM (ablation)LM (DRoBERTa) · MIMIC-III link predictionAUC: 51.44 -> 82.15Improved
add graph-aware fine-tuning to the plain LM (ablation)LM (DRoBERTa) · PubMed node classificationMacro-F1: 58.29 -> 60.42Improved
add graph-aware fine-tuning to the plain LM (ablation)LM (DRoBERTa) · MIMIC-III node classificationMacro-F1: 66.25 -> 75.16Improved
combine LM with RGCN instead of RGCN alone (ablation)RGCN · PubMed node classificationMacro-F1: 12.50 -> 13.83Mixed
combine LM with HGT instead of HGT alone (ablation)HGT · MIMIC-III link predictionAUC: 64.01 -> 65.01Improved
choose GPT-2 instead of DRoBERTa as the LM (ablation)LM · PubMed node classificationMacro-F1: 58.29 -> 59.43Mixed
choose GPT-2 instead of DRoBERTa as the LM (ablation)LM · PubMed link predictionAUC: 60.97 -> 51.71Hurt
choose XRoBERTa instead of DRoBERTa as the LM (ablation)LM · PubMed node classificationMacro-F1: 58.29 -> 40.10Hurt
remove the graph ID virtual node (ablation)WalkLM · MUTAGaccuracy: 81.39 -> 79.77Hurt
masked ratio m from 0.15 to 0.05 (ablation)WalkLM · PubMed node classificationMacro-F1: 60.42 -> 52.97Hurt
masked ratio m from 0.15 to 0.35 (ablation)WalkLM · PubMed node classificationMacro-F1: 60.42 -> 52.22Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy