G-Retriever graph tokens collapse into a generic soft prompt
A learned constant prompt that never sees the graph matches or beats G-Retriever on all three benchmarks.
Stories per day · 30 days
3 RSS
Relatedbaselines1correct-and-smooth1feature-propagation1graph-soft-prompting1g-retriever1kgqa1relational-deep-learning1relbench1token-collapse1
8 stories, newest first · one card per story
Stories tagged #gnn
Revisiting Simple Baselines for Relational Deep Learning
Simple feature and label propagation recover much heterogeneous GNN performance on RelBench tasks.
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
Researchers propose G2MLP, a curvature-guided distillation method that transfers GNN geometry into graph-free MLPs.
EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
EDiS sparsifies GNN training by caching edge-disjoint subgraphs and recomposing them each epoch under an edge budget.
QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision
QUFIG uses a circuit-DAG GNN to rank quantum gates by fault-injection impact under limited fidelity budgets.
Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
Dagger steals GNN models from hard-label APIs with higher fidelity and far fewer queries.
A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
DSS-GNN unifies GNN calibration, OOD detection, and shift robustness in one spectral representation.
Sybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and Autonomous Vehicles Using Dynamic Semi-supervised GNN
Sybil-TraceGuard, a dynamic semi-supervised spatio-temporal GNN, links fragmented Sybil pseudonyms in connected vehicles back to their source attackers.