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

Neelam Akula, Surbhi Kumar, Murat Kantarcioglu, Baris Coskunuzer
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:1630-1646, 2026.

Abstract

Many real-world graphs support multiple predictive tasks over the same underlying structure, creating an opportunity to reuse supervision across node classification (NC) and link prediction (LP). However, existing evaluations often rely on incompatible splits, observed-graph assumptions, and negative sampling rules, making conclusions about same-graph cross-task transfer unreliable. We formalize same-graph NC–LP transfer and propose a leakage-free protocol that fixes node and edge splits, uses a shared message-passing graph that excludes evaluated edges, and employs fixed negatives for LP. Across three backbones (GCN, GraphSAGE, GPS), we find transfer is strongly directional and predictable: NC$\to$LP is consistently beneficial on homophilic graphs, while LP$\to$NC is fragile and can even degrade accuracy under naive representation reuse. LP$\to$NC becomes reliably positive mainly in a structure-dominant regime where LP is easy but NC is unsaturated, suggesting LP acts as structural pretraining. Finally, we introduce CoTask Score (CTS) to summarize joint NC+LP utility when a shared encoder must serve both tasks, and show that simple dataset statistics, especially homophily, can guide mechanism choice and help avoid negative transfer.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-akula26a, title = {Same Graph Cross-Task Transfer in {GNN}s: Protocols and Predictors}, author = {Akula, Neelam and Kumar, Surbhi and Kantarcioglu, Murat and Coskunuzer, Baris}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {1630--1646}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/akula26a/akula26a.pdf}, url = {https://proceedings.mlr.press/v306/akula26a.html}, abstract = {Many real-world graphs support multiple predictive tasks over the same underlying structure, creating an opportunity to reuse supervision across node classification (NC) and link prediction (LP). However, existing evaluations often rely on incompatible splits, observed-graph assumptions, and negative sampling rules, making conclusions about same-graph cross-task transfer unreliable. We formalize same-graph NC–LP transfer and propose a leakage-free protocol that fixes node and edge splits, uses a shared message-passing graph that excludes evaluated edges, and employs fixed negatives for LP. Across three backbones (GCN, GraphSAGE, GPS), we find transfer is strongly directional and predictable: NC$\to$LP is consistently beneficial on homophilic graphs, while LP$\to$NC is fragile and can even degrade accuracy under naive representation reuse. LP$\to$NC becomes reliably positive mainly in a structure-dominant regime where LP is easy but NC is unsaturated, suggesting LP acts as structural pretraining. Finally, we introduce CoTask Score (CTS) to summarize joint NC+LP utility when a shared encoder must serve both tasks, and show that simple dataset statistics, especially homophily, can guide mechanism choice and help avoid negative transfer.} }
Endnote
%0 Conference Paper %T Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors %A Neelam Akula %A Surbhi Kumar %A Murat Kantarcioglu %A Baris Coskunuzer %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-akula26a %I PMLR %P 1630--1646 %U https://proceedings.mlr.press/v306/akula26a.html %V 306 %X Many real-world graphs support multiple predictive tasks over the same underlying structure, creating an opportunity to reuse supervision across node classification (NC) and link prediction (LP). However, existing evaluations often rely on incompatible splits, observed-graph assumptions, and negative sampling rules, making conclusions about same-graph cross-task transfer unreliable. We formalize same-graph NC–LP transfer and propose a leakage-free protocol that fixes node and edge splits, uses a shared message-passing graph that excludes evaluated edges, and employs fixed negatives for LP. Across three backbones (GCN, GraphSAGE, GPS), we find transfer is strongly directional and predictable: NC$\to$LP is consistently beneficial on homophilic graphs, while LP$\to$NC is fragile and can even degrade accuracy under naive representation reuse. LP$\to$NC becomes reliably positive mainly in a structure-dominant regime where LP is easy but NC is unsaturated, suggesting LP acts as structural pretraining. Finally, we introduce CoTask Score (CTS) to summarize joint NC+LP utility when a shared encoder must serve both tasks, and show that simple dataset statistics, especially homophily, can guide mechanism choice and help avoid negative transfer.
APA
Akula, N., Kumar, S., Kantarcioglu, M. & Coskunuzer, B.. (2026). Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:1630-1646 Available from https://proceedings.mlr.press/v306/akula26a.html.

Related Material