Kurt Keutzer


Reservoir Transformers
Sheng Shen | Alexei Baevski | Ari Morcos | Kurt Keutzer | Michael Auli | Douwe Kiela
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear “reservoir” layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until convergence, as well as overall performance, on various machine translation and (masked) language modelling tasks.

What’s Hidden in a One-layer Randomly Weighted Transformer?
Sheng Shen | Zhewei Yao | Douwe Kiela | Kurt Keutzer | Michael Mahoney
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

We demonstrate that, hidden within one-layer randomly weighted neural networks, there exist subnetworks that can achieve impressive performance, without ever modifying the weight initializations, on machine translation tasks. To find subnetworks for one-layer randomly weighted neural networks, we apply different binary masks to the same weight matrix to generate different layers. Hidden within a one-layer randomly weighted Transformer, we find that subnetworks that can achieve 29.45/17.29 BLEU on IWSLT14/WMT14. Using a fixed pre-trained embedding layer, the previously found subnetworks are smaller than, but can match 98%/92% (34.14/25.24 BLEU) of the performance of, a trained Transformersmall/base on IWSLT14/WMT14. Furthermore, we demonstrate the effectiveness of larger and deeper transformers in this setting, as well as the impact of different initialization methods.


SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Forrest Iandola | Albert Shaw | Ravi Krishna | Kurt Keutzer
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing

Humans read and write hundreds of billions of messages every day. Further, due to the availability of large datasets, large computing systems, and better neural network models, natural language processing (NLP) technology has made significant strides in understanding, proofreading, and organizing these messages. Thus, there is a significant opportunity to deploy NLP in myriad applications to help web users, social networks, and businesses. Toward this end, we consider smartphones and other mobile devices as crucial platforms for deploying NLP models at scale. However, today’s highly-accurate NLP neural network models such as BERT and RoBERTa are extremely computationally expensive, with BERT-base taking 1.7 seconds to classify a text snippet on a Pixel 3 smartphone. To begin to address this problem, we draw inspiration from the computer vision community, where work such as MobileNet has demonstrated that grouped convolutions (e.g. depthwise convolutions) can enable speedups without sacrificing accuracy. We demonstrate how to replace several operations in self-attention layers with grouped convolutions, and we use this technique in a novel network architecture called SqueezeBERT, which runs 4.3x faster than BERT-base on the Pixel 3 while achieving competitive accuracy on the GLUE test set. A PyTorch-based implementation of SqueezeBERT is available as part of the Hugging Face Transformers library: https://huggingface.co/squeezebert


Efficient Parallel CKY Parsing on GPUs
Youngmin Yi | Chao-Yue Lai | Slav Petrov | Kurt Keutzer
Proceedings of the 12th International Conference on Parsing Technologies