CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
Graph prompt learn- ing: A comprehensive survey and beyond.arXiv preprint arXiv:2311.16534
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
PromptDyG performs unsupervised test-time prompt adaptation on frozen dynamic graph models via entropy minimization to guarantee larger positive-negative pair margins and improve online predictions.
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
CHoE uses structure-conditioned experts, structure-aware routing with load balancing, and prompt-based semantic fusion to improve few-shot performance on cross-domain heterogeneous graph prompt learning tasks.
LR-GMP unifies graph prompting via a low-rank Graph Message Prompt paradigm to achieve better generalization than component-specific methods.
citing papers explorer
-
Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
-
PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
PromptDyG performs unsupervised test-time prompt adaptation on frozen dynamic graph models via entropy minimization to guarantee larger positive-negative pair margins and improve online predictions.
-
PLACE: Prompt Learning for Attributed Community Search in Large Graphs
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
-
CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts
CHoE uses structure-conditioned experts, structure-aware routing with load balancing, and prompt-based semantic fusion to improve few-shot performance on cross-domain heterogeneous graph prompt learning tasks.
-
Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
LR-GMP unifies graph prompting via a low-rank Graph Message Prompt paradigm to achieve better generalization than component-specific methods.