Home > Research > Publications & Outputs > Contrastive Training with More Data

Research

Associated organisational unit

Electronic data

  • 66_contrastive_training_with_more

    Final published version, 310 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

View graph of relations

Contrastive Training with More Data

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Published

Standard

Contrastive Training with More Data. / Mander, Stephen; Piao, Scott; Rahmani, Hossein.
2023. Paper presented at Eleventh International Conference on Learning Representations, Kigali, Rwanda.

Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review

Harvard

Mander, S, Piao, S & Rahmani, H 2023, 'Contrastive Training with More Data', Paper presented at Eleventh International Conference on Learning Representations, Kigali, Rwanda, 1/05/23. <https://dblp.org/db/conf/iclr/iclr2023tiny.html>

APA

Mander, S., Piao, S., & Rahmani, H. (2023). Contrastive Training with More Data. Paper presented at Eleventh International Conference on Learning Representations, Kigali, Rwanda. https://dblp.org/db/conf/iclr/iclr2023tiny.html

Vancouver

Mander S, Piao S, Rahmani H. Contrastive Training with More Data. 2023. Paper presented at Eleventh International Conference on Learning Representations, Kigali, Rwanda.

Author

Mander, Stephen ; Piao, Scott ; Rahmani, Hossein. / Contrastive Training with More Data. Paper presented at Eleventh International Conference on Learning Representations, Kigali, Rwanda.

Bibtex

@conference{962f22321a0844329304b511e29ea51f,
title = "Contrastive Training with More Data",
abstract = "This paper proposes a new method of contrastive training over multiple data points, focusing on the scaling issue present when using in-batch negatives. Our approach compares transformer training with dual encoders versus training with multiple encoders. Our method can provide a feasible approach to improve lossmodelling as encoders scale.",
author = "Stephen Mander and Scott Piao and Hossein Rahmani",
year = "2023",
month = may,
day = "1",
language = "English",
note = "Eleventh International Conference on Learning Representations, ICLR 2023 ; Conference date: 01-05-2023",
url = "https://iclr.cc/Conferences/2023",

}

RIS

TY - CONF

T1 - Contrastive Training with More Data

AU - Mander, Stephen

AU - Piao, Scott

AU - Rahmani, Hossein

PY - 2023/5/1

Y1 - 2023/5/1

N2 - This paper proposes a new method of contrastive training over multiple data points, focusing on the scaling issue present when using in-batch negatives. Our approach compares transformer training with dual encoders versus training with multiple encoders. Our method can provide a feasible approach to improve lossmodelling as encoders scale.

AB - This paper proposes a new method of contrastive training over multiple data points, focusing on the scaling issue present when using in-batch negatives. Our approach compares transformer training with dual encoders versus training with multiple encoders. Our method can provide a feasible approach to improve lossmodelling as encoders scale.

M3 - Conference paper

T2 - Eleventh International Conference on Learning Representations

Y2 - 1 May 2023

ER -