Timezone: »
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However, they are learned independently in each layer and sometimes fail to capture precise patterns. In this paper, we propose a novel and generic mechanism based on evolving attention to improve the performance of transformers. On one hand, the attention maps in different layers share common knowledge, thus the ones in preceding layers can instruct the attention in succeeding layers through residual connections. On the other hand, low-level and high-level attentions vary in the level of abstraction, so we adopt convolutional layers to model the evolutionary process of attention maps. The proposed evolving attention mechanism achieves significant performance improvement over various state-of-the-art models for multiple tasks, including image classification, natural language understanding and machine translation.
Author Information
Yujing Wang (Peking University)
Yaming Yang (MSRA)
Jiangang Bai (Peking University)
Mingliang Zhang (Peking University)
Jing Bai (Microsoft)
JING YU (Institute of Information Engineering, Chinese Academy of Sciences)
Ce Zhang (ETH Zurich)
Gao Huang (Tsinghua)
Yunhai Tong (Peking University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Evolving Attention with Residual Convolutions »
Tue. Jul 20th 04:00 -- 06:00 PM Room
More from the Same Authors
-
2022 : Spatially and Temporally Adaptive Neural Networks »
Gao Huang -
2022 Poster: Certifying Out-of-Domain Generalization for Blackbox Functions »
Maurice Weber · Linyi Li · Boxin Wang · Zhikuan Zhao · Bo Li · Ce Zhang -
2022 Spotlight: Certifying Out-of-Domain Generalization for Blackbox Functions »
Maurice Weber · Linyi Li · Boxin Wang · Zhikuan Zhao · Bo Li · Ce Zhang -
2021 Poster: Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks »
Nezihe Merve Gürel · Xiangyu Qi · Luka Rimanic · Ce Zhang · Bo Li -
2021 Spotlight: Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks »
Nezihe Merve Gürel · Xiangyu Qi · Luka Rimanic · Ce Zhang · Bo Li -
2021 Poster: 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed »
Hanlin Tang · Shaoduo Gan · Ammar Ahmad Awan · Samyam Rajbhandari · Conglong Li · Xiangru Lian · Ji Liu · Ce Zhang · Yuxiong He -
2021 Spotlight: 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed »
Hanlin Tang · Shaoduo Gan · Ammar Ahmad Awan · Samyam Rajbhandari · Conglong Li · Xiangru Lian · Ji Liu · Ce Zhang · Yuxiong He -
2020 Poster: Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript »
Fangcheng Fu · Yuzheng Hu · Yihan He · Jiawei Jiang · Yingxia Shao · Ce Zhang · Bin Cui -
2019 : Networking Lunch (provided) + Poster Session »
Abraham Stanway · Alex Robson · Aneesh Rangnekar · Ashesh Chattopadhyay · Ashley Pilipiszyn · Benjamin LeRoy · Bolong Cheng · Ce Zhang · Chaopeng Shen · Christian Schroeder · Christian Clough · Clement DUHART · Clement Fung · Cozmin Ududec · Dali Wang · David Dao · di wu · Dimitrios Giannakis · Dino Sejdinovic · Doina Precup · Duncan Watson-Parris · Gege Wen · George Chen · Gopal Erinjippurath · Haifeng Li · Han Zou · Herke van Hoof · Hillary A Scannell · Hiroshi Mamitsuka · Hongbao Zhang · Jaegul Choo · James Wang · James Requeima · Jessica Hwang · Jinfan Xu · Johan Mathe · Jonathan Binas · Joonseok Lee · Kalai Ramea · Kate Duffy · Kevin McCloskey · Kris Sankaran · Lester Mackey · Letif Mones · Loubna Benabbou · Lynn Kaack · Matthew Hoffman · Mayur Mudigonda · Mehrdad Mahdavi · Michael McCourt · Mingchao Jiang · Mohammad Mahdi Kamani · Neel Guha · Niccolo Dalmasso · Nick Pawlowski · Nikola Milojevic-Dupont · Paulo Orenstein · Pedram Hassanzadeh · Pekka Marttinen · Ramesh Nair · Sadegh Farhang · Samuel Kaski · Sandeep Manjanna · Sasha Luccioni · Shuby Deshpande · Soo Kim · Soukayna Mouatadid · Sunghyun Park · Tao Lin · Telmo Felgueira · Thomas Hornigold · Tianle Yuan · Tom Beucler · Tracy Cui · Volodymyr Kuleshov · Wei Yu · yang song · Ydo Wexler · Yoshua Bengio · Zhecheng Wang · Zhuangfang Yi · Zouheir Malki -
2019 Poster: Distributed Learning over Unreliable Networks »
Chen Yu · Hanlin Tang · Cedric Renggli · Simon Kassing · Ankit Singla · Dan Alistarh · Ce Zhang · Ji Liu -
2019 Oral: Distributed Learning over Unreliable Networks »
Chen Yu · Hanlin Tang · Cedric Renggli · Simon Kassing · Ankit Singla · Dan Alistarh · Ce Zhang · Ji Liu -
2019 Poster: DL2: Training and Querying Neural Networks with Logic »
Marc Fischer · Mislav Balunovic · Dana Drachsler-Cohen · Timon Gehr · Ce Zhang · Martin Vechev -
2019 Oral: DL2: Training and Querying Neural Networks with Logic »
Marc Fischer · Mislav Balunovic · Dana Drachsler-Cohen · Timon Gehr · Ce Zhang · Martin Vechev -
2018 Poster: Asynchronous Decentralized Parallel Stochastic Gradient Descent »
Xiangru Lian · Wei Zhang · Ce Zhang · Ji Liu -
2018 Poster: $D^2$: Decentralized Training over Decentralized Data »
Hanlin Tang · Xiangru Lian · Ming Yan · Ce Zhang · Ji Liu -
2018 Oral: $D^2$: Decentralized Training over Decentralized Data »
Hanlin Tang · Xiangru Lian · Ming Yan · Ce Zhang · Ji Liu -
2018 Oral: Asynchronous Decentralized Parallel Stochastic Gradient Descent »
Xiangru Lian · Wei Zhang · Ce Zhang · Ji Liu -
2017 Poster: ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning »
Hantian Zhang · Jerry Li · Kaan Kara · Dan Alistarh · Ji Liu · Ce Zhang -
2017 Talk: ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning »
Hantian Zhang · Jerry Li · Kaan Kara · Dan Alistarh · Ji Liu · Ce Zhang