Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention

20 March 2022

Papers citing "Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention"

33 / 33 papers shown

Title
Differentiable Subset Pruning of Transformer Heads Jiaoda Li Ryan Cotterell Mrinmaya Sachan 86 56 0 10 Aug 2021
Learned Token Pruning for Transformers Sehoon Kim Sheng Shen D. Thorsley A. Gholami Woosuk Kwon Joseph Hassoun Kurt Keutzer 62 155 0 02 Jul 2021
Skip-Convolutions for Efficient Video Processing A. Habibian Davide Abati Taco S. Cohen B. Bejnordi 100 50 0 23 Apr 2021
Keyword Transformer: A Self-Attention Model for Keyword Spotting Axel Berg Mark O'Connor M. T. Cruz 66 135 0 01 Apr 2021
End-to-End Multi-Channel Transformer for Speech Recognition Feng-Ju Chang Martin H. Radfar Athanasios Mouchtaris Brian King Siegfried Kunzmann ViT 68 33 0 08 Feb 2021
Video Transformer Network Daniel Neimark Omri Bar Maya Zohar Dotan Asselmann ViT 264 432 0 01 Feb 2021
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet Li-xin Yuan Yunpeng Chen Tao Wang Weihao Yu Yujun Shi Zihang Jiang Francis E. H. Tay Jiashi Feng Shuicheng Yan ViT 133 1,939 0 28 Jan 2021
Training data-efficient image transformers & distillation through attention Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles Hervé Jégou ViT 384 6,768 0 23 Dec 2020
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning Hanrui Wang Zhekai Zhang Song Han 116 390 0 17 Dec 2020
Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset Xie Chen Yu-Huan Wu Zhenghao Wang Shujie Liu Jinyu Li 114 174 0 22 Oct 2020
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search Gyuwan Kim Kyunghyun Cho 74 96 0 14 Oct 2020
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech Andy T. Liu Shang-Wen Li Hung-yi Lee SSL 124 358 0 12 Jul 2020
Language Models are Few-Shot Learners Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan ... Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever Dario Amodei BDL 795 42,055 0 28 May 2020
Conformer: Convolution-augmented Transformer for Speech Recognition Anmol Gulati James Qin Chung-Cheng Chiu Niki Parmar Yu Zhang ... Wei Han Shibo Wang Zhengdong Zhang Yonghui Wu Ruoming Pang 223 3,139 0 16 May 2020
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices Zhiqing Sun Hongkun Yu Xiaodan Song Renjie Liu Yiming Yang Denny Zhou MQ 109 816 0 06 Apr 2020
Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning Mitchell A. Gordon Kevin Duh Nicholas Andrews VLM 53 340 0 19 Feb 2020
Structured Pruning of a BERT-based Question Answering Model J. Scott McCarley Rishav Chakravarti Avirup Sil 54 53 0 14 Oct 2019
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter Victor Sanh Lysandre Debut Julien Chaumond Thomas Wolf 232 7,520 0 02 Oct 2019
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations Zhenzhong Lan Mingda Chen Sebastian Goodman Kevin Gimpel Piyush Sharma Radu Soricut SSL AIMat 368 6,455 0 26 Sep 2019
Patient Knowledge Distillation for BERT Model Compression S. Sun Yu Cheng Zhe Gan Jingjing Liu 134 837 0 25 Aug 2019
RoBERTa: A Robustly Optimized BERT Pretraining Approach Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy M. Lewis Luke Zettlemoyer Veselin Stoyanov AIMat 659 24,464 0 26 Jul 2019
Are Sixteen Heads Really Better than One? Paul Michel Omer Levy Graham Neubig MoE 100 1,062 0 25 May 2019
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned Elena Voita David Talbot F. Moiseev Rico Sennrich Ivan Titov 114 1,141 0 23 May 2019
Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding Xiaodong Liu Pengcheng He Weizhu Chen Jianfeng Gao FedML 54 182 0 20 Apr 2019
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks Raphael Tang Yao Lu Linqing Liu Lili Mou Olga Vechtomova Jimmy J. Lin 69 421 0 28 Mar 2019
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin Ming-Wei Chang Kenton Lee Kristina Toutanova VLM SSL SSeg 1.8K 94,891 0 11 Oct 2018
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition Pete Warden 86 1,619 0 09 Apr 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 233 3,473 0 09 Mar 2018
Attention Is All You Need Ashish Vaswani Noam M. Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan Gomez Lukasz Kaiser Illia Polosukhin 3DV 701 131,652 0 12 Jun 2017
Delta Networks for Optimized Recurrent Network Computation Daniel Neil Junhaeng Lee T. Delbruck Shih-Chii Liu 90 66 0 16 Dec 2016
Structured Pruning of Deep Convolutional Neural Networks S. Anwar Kyuyeon Hwang Wonyong Sung 124 748 0 29 Dec 2015
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding Song Han Huizi Mao W. Dally 3DGS 259 8,842 0 01 Oct 2015
Learning both Weights and Connections for Efficient Neural Networks Song Han Jeff Pool J. Tran W. Dally CVBM 313 6,681 0 08 Jun 2015