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.
Making machine learning robust against adversarial inputs,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Spectrally unstable nodes are identified via graph-spectral distortion analysis as primary drivers of reliability failures; isolating them yields a stable subgraph for learning with propagation-based recovery for the isolated nodes, improving performance across GNNs and spectral clustering under攻击s.
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.
-
Spectrally unstable nodes drive reliability failures in graph learning
Spectrally unstable nodes are identified via graph-spectral distortion analysis as primary drivers of reliability failures; isolating them yields a stable subgraph for learning with propagation-based recovery for the isolated nodes, improving performance across GNNs and spectral clustering under攻击s.