AI Paper Atlas

Research map / Graph learning / GNN architectures

G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation

Jun Chen, Ziyue Qiao, Qin Zhang, Kaize Ding, Xiao Luo

ICLR 2026 · Graph learning › GNN architectures · approach: Graph structure learning

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 parameter merging to build the unified model instead of using the pretrained model (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 72.2 -> 74.2Improved
add node-level MoE adapters (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 72.4 -> 74.2Improved
add graph-level MoE adapters (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 70.2 -> 74.2Improved
add the topology-aware Wasserstein distance loss (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 73.2 -> 74.2Improved
add the L1 distance (L_MD) loss (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 73.5 -> 74.2Improved
increase adapter rank from 10 to 30 (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 72.9 -> 73.9Improved
increase adapter rank from 30 to 50 (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 73.9 -> 73.8No clear effect
select more experts in top-k routing (k from 1 to 8) (ablation)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%)Mixed
replace adapters-only inference (G-Merging-s) by MoE adaptersG-Merging · 8 molecular tasks (GIN edgepred)average ROC-AUC (%): 73.1 -> 73.1No clear effect
replace adapters-only inference (G-Merging-s) by MoE adaptersG-Merging · 8 molecular tasks (GCN contextpred)average ROC-AUC (%): 68.8 -> 68.9No clear effect
G-Merging versus best baseline merging method (EMR-Merging)G-Merging · 8 molecular tasks (GIN contextpred)average ROC-AUC (%): 71.5 -> 74.0Improved
G-Merging versus best baseline merging method (EMR-Merging)G-Merging · 8 molecular tasks (GCN contextpred)average ROC-AUC (%): 66.4 -> 68.9Improved

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