Preprint · 2026 · Open access

Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds

Lakshani Manamperi, Disumi Pathirana, Thiwanka Pathirana, Nipun Premarathna, Kutila Gunasekera

arXiv (Cornell University) · Published 20 May 2026 · DOI 10.48550/arxiv.2605.20723

Open PDFView at the publisherCite this paper

In brief

“Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds” is a 2026 preprint by Lakshani Manamperi and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
0
References
19
Authors
5

Abstract

Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4 GB RAM envelope of commodity Android handsets. We present the DNN pipeline scheduling subsystem of CROWDio, which achieves practical ONNX inference across resource-constrained Android workers without model modification, by distributing memory pressure across devices via five mechanisms: JIT deferred partition loading, a single-partition-resident constraint, a 4-tier affinity scheduler, a zlib-compressed tensor transport, and a streaming 1:1 dependency model. Evaluated on DistilBERT (Sanh et al., 2019) (approximately 67 M parameters, SST-2) across five Android handsets over ten runs, our system holds peak per-device RSS to 43+-2 MB and limits battery draw to 50+-3 mAh per run, while streaming concurrency cuts batch latency 34% below barrier synchronisation.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Manamperi, L., Pathirana, D., Pathirana, T., Premarathna, N., & Gunasekera, K. (2026). Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20723

MLA 9

Manamperi, Lakshani, et al. “Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.20723.

Chicago

Manamperi, Lakshani, Disumi Pathirana, Thiwanka Pathirana, Nipun Premarathna, and Kutila Gunasekera. 2026. “Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20723.

Harvard

Manamperi, L. et al. (2026) ‘Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds’, arXiv (Cornell University). doi:10.48550/arxiv.2605.20723.

IEEE

L. Manamperi, D. Pathirana, T. Pathirana, N. Premarathna, and K. Gunasekera, “Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.20723.

BibTeX

@misc{manamperi2026memory,
  title     = {{Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds}},
  author    = {Manamperi, Lakshani and Pathirana, Disumi and Pathirana, Thiwanka and Premarathna, Nipun and Gunasekera, Kutila},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.20723},
  url       = {https://doi.org/10.48550/arxiv.2605.20723}
}

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

  • edge machine learning
  • transformer models
  • tensor compression
  • streaming inference
  • battery consumption
  • DistilBERT
  • mobile devices

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Manamperi, L., Pathirana, D., Pathirana, T., Premarathna, N., & Gunasekera, K. (2026). Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20723

How many times has this paper been cited?

0 times, according to OpenAlex on 19 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Lakshani Manamperi, Disumi Pathirana, Thiwanka Pathirana, Nipun Premarathna, Kutila Gunasekera.

What is the DOI of this paper?

10.48550/arxiv.2605.20723, permanently at https://doi.org/10.48550/arxiv.2605.20723. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.