Inductive Knowledge Graph Wave Networks
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2960-2968.
https://doi.org/10.24963/ijcai.2026/329
Keywords
- Machine Learning: Representation learning
- Data Mining: Knowledge graphs and knowledge base completion
- Knowledge Representation and Reasoning: Semantic Web
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.
@inproceedings{ijcai2026p329,
title = {Inductive Knowledge Graph Wave Networks},
author = {Pirrò, Giuseppe},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {2960--2968},
year = {2026},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2026/329},
url = {https://doi.org/10.24963/ijcai.2026/329},
}
TY - CPAPER TI - Inductive Knowledge Graph Wave Networks AU - Pirrò, Giuseppe T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 2960 EP - 2968 DO - 10.24963/ijcai.2026/329 UR - https://doi.org/10.24963/ijcai.2026/329 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
