AI RESEARCH
SeedER: Seed-and-Expand Retrieval from Knowledge Graphs
arXiv CS.LG
•
ArXi:2605.23753v1 Announce Type: new Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense embedding methods struggle with multi-hop compositional queries. Existing agent-based graph exploration approaches, while expressive, are often too expensive for large-scale retrieval. We