---
title: "Inductive Knowledge Graph Wave Networks"
authors:
  - "Giuseppe Pirrò"
doi: "10.24963/ijcai.2026/329"
url: "https://ijcai.org/proceedings/2026/329"
pdf: "https://ijcai.org/proceedings/2026/0329.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2960-2968"
track: "Main Track"
keywords:
  - "Machine Learning: Representation learning"
  - "Data Mining: Knowledge graphs and knowledge base completion"
  - "Knowledge Representation and Reasoning: Semantic Web"
---

# Inductive Knowledge Graph Wave Networks

Giuseppe Pirrò

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2960-2968. DOI: [10.24963/ijcai.2026/329](https://doi.org/10.24963/ijcai.2026/329)

## 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.