AI Paper Atlas

Research map / Graph learning / GNN architectures

Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors

Neelam Akula, Surbhi Kumar, Murat Kantarcioglu, Baris Coskunuzer

ICML 2026 · Graph learning › GNN architectures · approach: Graph structure learning · 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
transfer NC supervision to LP via multi-view or joint training on homophilic graphsGCN, GraphSAGE, GPS · CORA, CITESEER, PUBMED (NC->LP)LP AUC gain: CORA GCN Joint +12.3 AUC pointsImproved
reuse LP representation by replacing node features (ET Rep) for NCGCN · CORA, CITESEER, PUBMED (LP->NC)NC accuracy gain: -12.7, -16.8, -21.4Hurt
LP->NC transfer via ET Concat/Joint on structure-dominant graphsGCN · USA, EUROPE, BRAZIL (LP->NC)NC accuracy gain: USA ET Concat +7.8; BRAZIL Joint +13.7Improved
LP->NC transfer on homophilic graphs with warm start, MV or JointGCN · CORA, CITESEER, PUBMED (LP->NC)NC accuracy gain: WS +0.6, +0.5, +0.1No clear effect
NC->LP via ET Rep on heterophilic ROMAN-EMPIREGCN, GraphSAGE · ROMAN-EMPIRE (NC->LP)LP AUC gain: -10.6 (GCN), -12.5 (GraphSAGE)Hurt
NC->LP warm start on USAGCN · USA (NC->LP)LP AUC gain: +0.3 (WS)No clear effect
add Joint training for GPS on ROMAN-EMPIRE NC->LPGPS · ROMAN-EMPIRE (NC->LP)LP AUC gain: +27.9 over base 68.8Improved
couple objectives with MV or Joint rather than post hoc reuse on heterophilic graphsGCN, GraphSAGE, GPS · TEXAS, CORNELL, WISCONSIN, ACTOR, ROMAN-EMPIRECoTask Score: TEXAS GPS Joint 38.4 vs ET Rep 19.6Improved
homophily as predictor of NC->LP gainsGCN · 11 datasetsPearson r with gain: ET Concat r with Hn 0.904Improved
homophily as predictor of LP->NC gainsGCN · 11 datasetsPearson r with gain: ET Rep He -0.114, Hn -0.353No clear effect
clustering coefficient as predictor of LP->NC gains for ET ConcatGCN · 11 datasetsPearson r with gain: r = 0.782Improved
transfer on mixed-regime graphs measured by CTSGraphSAGE, GPS · USA, EUROPE, BRAZILCoTask Score: EUROPE GPS MV -15.4; BRAZIL GPS ET Con 13.9Mixed

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