HyDRA uses multi-scale hypergraph retrieval-augmented generation and an LLM fusion step to align entities across temporal knowledge graphs with mismatched time granularities and structure, and the paper introduces two new harder benchmarks.
Inductive meta-path learning for schema-complex heterogeneous information networks,
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.DB 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Temporal Knowledge Graph Alignment in the Wild
HyDRA uses multi-scale hypergraph retrieval-augmented generation and an LLM fusion step to align entities across temporal knowledge graphs with mismatched time granularities and structure, and the paper introduces two new harder benchmarks.