Journal article · 2026 · Open access
CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference
IEEE Access, 14, 38544–38562 · Published 1 January 2026 · DOI 10.1109/access.2026.3671798
In brief
“CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference” is a 2026 journal article by Zijian Shen and 4 co-authors, published in IEEE Access. OpenAlex counts 26 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Access.
- Citations
- 26
- Most cited in
- 2026 (26)
- Field-weighted impact
- 57.96
- References
- 44
- Authors
- 5
Abstract
Recommender systems have become ubiquitous in modern online services, yet their deployment across diverse hardware accelerators remains challenging due to significant performance variations. Contemporary deep learning recommendation models (DLRMs), such as DeepFM and NGCF, exhibit substantial inference latency differences when executed on NVIDIA GPUs,AMDGPUs, and Google TPUs, primarily due to architectural disparities and vendor-specific optimization strategies. Existing graph optimization frameworks are typically designed for specific hardware backends, lacking the flexibility to generate portable high-performance implementations across heterogeneous accelerators. This paper presents CAGR (Cross-Accelerator Graph Rewriting), a novel framework that achieves performance-portable inference optimization for recommendation models through three key innovations: (1) a hardware-aware graph rewriting engine that dynamically selects optimal operator implementations by analyzing compute-to-memory bandwidth ratios and operator density characteristics; (2) a reinforcement learning-based transformation policy that learns cross-platform optimization strategies without exhaustive search; and (3) a heterogeneous pipeline architecture enabling “optimize once, deploy across supported backends” semantics. We implement CAGR with support for multiple kernel backends including Triton, cuBLAS, MIOpen, and oneDNN, and demonstrate its effectiveness on the Avazu CTR prediction dataset. Experimental results show that CAGR achieves 1.8-3.2× speedup over baseline implementations across NVIDIA V100, AMD MI100, and Google TPU v3 platforms, while reducing optimization time by 67% compared to platform-specific auto-tuning approaches. Furthermore, CAGR maintains 92-96% of reference optimized performance with zero manual intervention, demonstrating practical viability for production recommendation systems requiring multi-vendor deployment.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Shen, Z., Zhao, W., Wang, B., Wang, Z., & Shang, W. (2026). CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference. IEEE Access, 14, 38544–38562. https://doi.org/10.1109/access.2026.3671798
MLA 9
Shen, Zijian, et al. “CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference.” IEEE Access, vol. 14, 2026, pp. 38544–38562. https://doi.org/10.1109/access.2026.3671798.
Chicago
Shen, Zijian, Wenyu Zhao, Boyuan Wang, Zimeng Wang, and Wenbin Shang. 2026. “CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference.” IEEE Access 14: 38544–38562. https://doi.org/10.1109/access.2026.3671798.
Harvard
Shen, Z. et al. (2026) ‘CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference’, IEEE Access, 14, pp. 38544–38562. doi:10.1109/access.2026.3671798.
IEEE
Z. Shen, W. Zhao, B. Wang, Z. Wang, and W. Shang, “CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference,” IEEE Access, vol. 14, pp. 38544–38562, 2026, doi: 10.1109/access.2026.3671798.
BibTeX
@article{shen2026cagr,
title = {{CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference}},
author = {Shen, Zijian and Zhao, Wenyu and Wang, Boyuan and Wang, Zimeng and Shang, Wenbin},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {38544--38562},
doi = {10.1109/access.2026.3671798},
url = {https://doi.org/10.1109/access.2026.3671798}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- graph transformation
- deep learning recommendation models
- performance portability
- operator selection
- NVIDIA GPUs
- AMD GPUs
- inference latency
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Shen, Z., Zhao, W., Wang, B., Wang, Z., & Shang, W. (2026). CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference. IEEE Access, 14, 38544–38562. https://doi.org/10.1109/access.2026.3671798
How many times has this paper been cited?
26 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Access: sign in and open the full text from this page.
Who wrote this paper?
Zijian Shen, Wenyu Zhao, Boyuan Wang, Zimeng Wang, Wenbin Shang.
What is the DOI of this paper?
10.1109/access.2026.3671798, permanently at https://doi.org/10.1109/access.2026.3671798. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.