Metraipolis › archive › dc_8cf5ca4b6367
Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing — arXiv:2609.34499
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34499
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:41.938Z
- SHA-256 of the archived text
95c76a80cda0f6141fd9b493948e830d7c27cd2cd28bcb2f4eca56b34415919d- Stable URL of this page
https://metraipolis.com/documento/dc_8cf5ca4b6367
How to cite
Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing — arXiv:2609.34499 — arXiv (en), https://arxiv.org/abs/2609.34499 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cf5ca4b6367 (Metraipolis archive dc_8cf5ca4b6367, sha256 95c76a80cda0f6141fd9b493948e830d7c27cd2cd28bcb2f4eca56b34415919d)
BibTeX
@misc{dc8cf5ca4b6367,
title = {Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing — arXiv:2609.34499},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34499},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cf5ca4b6367; sha256 95c76a80cda0f6141fd9b493948e830d7c27cd2cd28bcb2f4eca56b34415919d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34499. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph neural networks (GNNs) excel at representation learning on Knowledge Graphs (KGs), achieving stateof-the-art performance on tasks like link prediction or entity classification. However, their high computational complexity, inherent to their user-defined message passing (MP) algorithm, still prohibits their widespread adoption, especially for large KGs. Current efforts to mitigate the scalability bottlenecks of GNNs on KGs, such as subgraph sampling, are often task- and model-specific, and do not reliably guarantee lossless (if applicable) runtime/space reductions. To address this, we extend Relational Sparse Matrix Multiplication (RSPMM), originally designed to losslessly lower the space complexity of composition-based MP with pointwise composition functions, to support more expressive functions (e.g., 2x2 block-diagonal matrix multiplication, Givens rotation, circular correlation). Our method delivers significant task-independent reductions in runtime and space for current GNNs on KGs and facilitates efficient re-implementations of GNNs that maintain near state-of-the-art performance on challenging KG tasks, for a fraction of computational costs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34499 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:03.024Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).