A joint language-model and knowledge-graph pre-training method reports large F1 improvements for Ethereum phishing detection and de-anonymization, but protocol ambiguities remain.
Measuring and relieving the over-smoothing problem for graph neural networks from the topological view,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
KGBERT4Eth: A Feature-Complete Transformer Powered by Knowledge Graph for Multi-Task Ethereum Fraud Detection
A joint language-model and knowledge-graph pre-training method reports large F1 improvements for Ethereum phishing detection and de-anonymization, but protocol ambiguities remain.