High-Efficiency Device-Cloud Collaborative Transformer Model

Penghao Jiang, Ke Xin, Chunxi Li, Yinsi Zhou; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 2204-2210

Abstract


Natural Language Processing (NLP) experts have had significant success with unsupervised language pre-training techniques. However, compared to typical NLP models, modern self-attention models require far more computational and memory resources than conventional NLP models, making pre-training or even fine-tuning them quite costly. It drastically restricts their success and uses in a variety of fields. To improve the efficiency, we propose Device-Cloud Collaborative Transformer for an efficient language model, which is a framework across cloud and device, and is designed to encourage learning of representations that generalize better to many different tasks. Specifically, we design Device-Cloud Collaborative Transformer architecture of large language models that benefits both cloud modeling and device modeling. Experimental results demonstrate the effectiveness of our proposed method.

Related Material


[pdf]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Penghao and Xin, Ke and Li, Chunxi and Zhou, Yinsi}, title = {High-Efficiency Device-Cloud Collaborative Transformer Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {2204-2210} }