Qiu, S., Xia, C. and Wang, Z. orcid.org/0000-0001-6157-0662 (2025) Accelerating Tensor-train Decomposition on Graph Neural Networks. In: 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 39th IEEE International Parallel & Distributed Processing Symposium, 03-07 Jun 2025, Milan, Italy. IEEE , pp. 130-141. ISBN: 979-8-3315-3238-3 ISSN: 1530-2075 EISSN: 1530-2075
Abstract
Memory footprint is a major concern when training graph neural networks (GNNs) on large graph data. Tensor-train decomposition (TTD) offers a potential solution by representing high-dimensional tensors with a set of smaller tensors, reducing memory overhead. However, existing TTD-based solutions for GNNs fail to reuse intermediate computation results and minimize memory data transfers to improve GNN performance. We introduce FALCON, a software framework to accelerate TTDbased GNN training. FALCON leverages the observation that a small subset of graph nodes with high edge degrees are frequently accessed, enabling the caching of intermediate results to reduce redundant computation and data transfers. Additionally, it incorporates multi-level graph partitioning and kernel optimization techniques to boost computational efficiency. We evaluated FALCON using three real-world datasets on three GPU platforms-NVIDIA 3090, 4090, and A100. Experimental results show that FALCON outperforms previous TTD-based frameworks, delivering a 1.3 to 8.17× improvement in throughput while maintaining comparable or better efficiencies in memory footprint and model accuracy.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Keywords: | graph neural networks, code optimization, tensor-train decomposition |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EPSRC (Engineering and Physical Sciences Research Council) EP/X018202/1 EPSRC (Engineering and Physical Sciences Research Council) EP/X037304/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 11 Mar 2025 11:01 |
Last Modified: | 26 Aug 2025 18:27 |
Published Version: | https://ieeexplore.ieee.org/document/11078524 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/IPDPS64566.2025.00020 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:224242 |