AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang

ICML 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 0 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 norm rescaling of generated low-rank matrix (ablation)GaRA, full tuning data · Cora (zero-shot)accuracy: 0.164 -> 0.251 (+53.04%)Improved
add norm rescaling (ablation)GaRA, full tuning data · AmazonPhoto link predictionaccuracy: 0.539 -> 0.708Improved
add norm rescaling (ablation)GaRA, partial tuning data · WikiCS (zero-shot)accuracy: 0.611 -> 0.664Improved
add norm rescaling (ablation)GaRA, partial tuning data · AmazonPhoto link predictionaccuracy: 0.527 -> 0.529Improved
increase tuning data from Partial to Full (ablation)GaRA without norm rescaling · Cora (zero-shot)accuracy: 0.203 -> 0.164Hurt
add weight-level injection to input-level subgraph injection (input+weight) (ablation)UniGTE-based framework · zero-shot datasets (Partial setup)performanceImproved
inject weight update at layer 21 instead of layers 1, 11, 31, 32 (ablation)GaRA on Vicuna-7B · average over node and link datasetsaverage performanceImproved
generate the augmented left low-rank matrix instead of the right matrix (ablation)GaRA · average over node and link datasetsaverage performanceImproved
generate weights from whole-graph representation instead of subgraph, task-description or random inputs (ablation)GaRA · zero-shot datasetsperformanceImproved
generate weights from subgraph features instead of non-graph features (ablation)GaRA · zero-shot datasetsperformanceNo clear effect
add GaRA weight generation compared to UniGTEUniGTE · training and inference costs/sample: 1.28 -> 1.46 train; 0.67 -> 0.71 inferenceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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