Inductive Knowledge Graph Wave Networks

Giuseppe Pirrò

IJCAI 20260 citations

Inductive Knowledge Graph Wave Networks

Abstract

Inductive knowledge graph reasoning (IKGR) requires generalization to entities and relation types not seen during training. We introduce Knowledge Graph Wave Networks (KGWN), an IKGR approach that learns adaptive per-relation wave operators to control relation-dependent propagation, along with velocity normalization ensuring stability at any propagation depth. Experiments demonstrate state-of-the-art results on inductive benchmarks and competitive transductive performance.

Data Mining: Knowledge graphs and knowledge base completionKnowledge Representation and Reasoning: Semantic WebMachine Learning: Representation learning

BibTeX

@inproceedings{ijcai2026_inductiveknowled,
  title = {Inductive Knowledge Graph Wave Networks},
  author = {Giuseppe Pirrò},
  booktitle = {IJCAI 2026},
  year = {2026}
}