The University of Southampton
University of Southampton Institutional Repository

Accelerating position-aware top-k listnet for ranking under custom precision regimes

Accelerating position-aware top-k listnet for ranking under custom precision regimes
Accelerating position-aware top-k listnet for ranking under custom precision regimes

Document ranking is used to order query results by relevance with ranking models. ListNet is a well-know ranking approach for constructing and training learning to rank models. Compared with traditional learning approaches, ListNet delivers better accuracy, but is computationally too expensive to learn models with large datasets due to the large number of permutations involved in computing the gradients. This paper introduces a position-aware sampling approach, which takes the importance of ranking positions into account and shows better accuracy than previous sampling methods. We also propose an effective quantisation method based on FPGA devices for the ListNet algorithm, which organises the gradient values to several batches, and associates each batch with a different fractional precision. We implemented our approach on a Xilinx Ultrascale+ board and applied it to the MQ 2008 benchmark dataset for ranking. The experiment results show a 4.42x speedup over an Nvidia GTX 1080T GPU implementation with 2% accuracy loss.

Acceleration, Fixed point, ListNet, Quantisation, Ranking
81-87
IEEE
Li, Qiang
411fba27-9768-49a4-b313-b96f4004587f
Wang, Erwei
afc5ad5b-35d6-4333-8ff1-3df5bf433a3c
Fleming, Shane T.
1a7f7be0-0c3f-4125-9298-5b5a6e0bc76e
Thomas, David B.
5701997d-7de3-4e57-a802-ea2bd3e6ab6c
Cheung, Peter Y.K.
7a175b08-9e60-4f7c-bf75-bda5e529fefd
Sourdis, Ioannis
Bouganis, Christos-Savvas
Alvarez, Carlos
Toledo Diaz, Leonel Antonio
Valero, Pedro
Martorell, Xavier
Li, Qiang
411fba27-9768-49a4-b313-b96f4004587f
Wang, Erwei
afc5ad5b-35d6-4333-8ff1-3df5bf433a3c
Fleming, Shane T.
1a7f7be0-0c3f-4125-9298-5b5a6e0bc76e
Thomas, David B.
5701997d-7de3-4e57-a802-ea2bd3e6ab6c
Cheung, Peter Y.K.
7a175b08-9e60-4f7c-bf75-bda5e529fefd
Sourdis, Ioannis
Bouganis, Christos-Savvas
Alvarez, Carlos
Toledo Diaz, Leonel Antonio
Valero, Pedro
Martorell, Xavier

Li, Qiang, Wang, Erwei, Fleming, Shane T., Thomas, David B. and Cheung, Peter Y.K. (2019) Accelerating position-aware top-k listnet for ranking under custom precision regimes. Sourdis, Ioannis, Bouganis, Christos-Savvas, Alvarez, Carlos, Toledo Diaz, Leonel Antonio, Valero, Pedro and Martorell, Xavier (eds.) In Proceedings - 29th International Conference on Field-Programmable Logic and Applications, FPL 2019. IEEE. pp. 81-87 . (doi:10.1109/FPL.2019.00022).

Record type: Conference or Workshop Item (Paper)

Abstract

Document ranking is used to order query results by relevance with ranking models. ListNet is a well-know ranking approach for constructing and training learning to rank models. Compared with traditional learning approaches, ListNet delivers better accuracy, but is computationally too expensive to learn models with large datasets due to the large number of permutations involved in computing the gradients. This paper introduces a position-aware sampling approach, which takes the importance of ranking positions into account and shows better accuracy than previous sampling methods. We also propose an effective quantisation method based on FPGA devices for the ListNet algorithm, which organises the gradient values to several batches, and associates each batch with a different fractional precision. We implemented our approach on a Xilinx Ultrascale+ board and applied it to the MQ 2008 benchmark dataset for ranking. The experiment results show a 4.42x speedup over an Nvidia GTX 1080T GPU implementation with 2% accuracy loss.

This record has no associated files available for download.

More information

Published date: 8 September 2019
Venue - Dates: 29th International Conferenceon Field-Programmable Logic and Applications, FPL 2019, , Barcelona, Spain, 2019-09-09 - 2019-09-13
Keywords: Acceleration, Fixed point, ListNet, Quantisation, Ranking

Identifiers

Local EPrints ID: 453680
URI: http://eprints.soton.ac.uk/id/eprint/453680
PURE UUID: d252ef4d-f2d9-4ae4-b8a8-82765b83d5a2
ORCID for David B. Thomas: ORCID iD orcid.org/0000-0002-9671-0917

Catalogue record

Date deposited: 20 Jan 2022 17:45
Last modified: 17 Mar 2024 04:10

Export record

Altmetrics

Contributors

Author: Qiang Li
Author: Erwei Wang
Author: Shane T. Fleming
Author: David B. Thomas ORCID iD
Author: Peter Y.K. Cheung
Editor: Ioannis Sourdis
Editor: Christos-Savvas Bouganis
Editor: Carlos Alvarez
Editor: Leonel Antonio Toledo Diaz
Editor: Pedro Valero
Editor: Xavier Martorell

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×