T2T-LA is an LLM agent that generates a useful graph topology in one shot from failed topologies and scores without feature access or task knowledge.
Adversarial attacks on graph neural networks via meta learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
Supervised GNNs show higher baseline accuracy on community detection while unsupervised ones like DMoN prove more resilient to attribute shifts, edge deletions, and adversarial perturbations, with stronger communities reducing performance drops.
citing papers explorer
-
T2T-LA: A Topology-to-Topology LLM Agent for Graph Learning with Neither Feature Access nor Task Knowledge
T2T-LA is an LLM agent that generates a useful graph topology in one shot from failed topologies and scores without feature access or task knowledge.
-
Community detection robustness of graph neural networks
Supervised GNNs show higher baseline accuracy on community detection while unsupervised ones like DMoN prove more resilient to attribute shifts, edge deletions, and adversarial perturbations, with stronger communities reducing performance drops.