Long Short-Term Attention

被引:3
|
作者
Zhong, Guoqiang [1 ]
Lin, Xin [1 ]
Chen, Kang [1 ]
Li, Qingyang [1 ]
Huang, Kaizhu [2 ]
机构
[1] Ocean Univ China, Dept Comp Sci & Technol, Qingdao 266100, Peoples R China
[2] Xian Jiaotong Liverpool Univ, Dept Elect & Elect Engn, SIP, Suzhou 215123, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Machine learning; Sequence learning; Attention mechanism; Long short-term memory; Long short-term attention; BIDIRECTIONAL LSTM; SALIENCY DETECTION; BOTTOM-UP; FRAMEWORK;
D O I
10.1007/978-3-030-39431-8_5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have no the attention mechanism. For example, the long short-term memory (LSTM) network is able to remember sequential information, but it cannot pay special attention to part of the sequences. In this paper, we present a novel model called long short-term attention (LSTA), which seamlessly integrates the attention mechanism into the inner cell of LSTM. More than processing long short term dependencies, LSTA can focus on important information of the sequences with the attention mechanism. Extensive experiments demonstrate that LSTA outperforms LSTM and related models on the sequence learning tasks.
引用
收藏
页码:45 / 54
页数:10
相关论文
共 50 条
  • [1] A forecast model of short-term wind speed based on the attention mechanism and long short-term memory
    Xing, Wang
    Qi-liang, Wu
    Gui-rong, Tan
    Dai-li, Qian
    Ke, Zhou
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (15) : 45603 - 45623
  • [2] A forecast model of short-term wind speed based on the attention mechanism and long short-term memory
    Wang Xing
    Wu Qi-liang
    Tan Gui-rong
    Qian Dai-li
    Zhou Ke
    Multimedia Tools and Applications, 2024, 83 : 45603 - 45623
  • [3] LSTA: Long Short-Term Attention for Egocentric Action Recognition
    Sudhakaran, Swathikiran
    Escalera, Sergio
    Lanz, Oswald
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9946 - 9955
  • [4] Long- and Short-term Attention Network for Knowledge Tracing
    Xu, Liancheng
    Wang, Guangchao
    Guo, Lei
    Wang, Xinhua
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [5] Short-term Load Forecasting by Long- and Short-term Temporal Networks With Attention Based on Modal Decomposition
    Qiao S.
    Wang L.
    Zhang P.
    Yan Q.
    Wang G.
    Dianwang Jishu/Power System Technology, 2022, 46 (10): : 3940 - 3951
  • [6] Recommendation Based on Users' Long-Term and Short-Term Interests with Attention
    Tan, Qiaoqiao
    Liu, Fang'ai
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2019, 2019
  • [7] Long Short-Term Memory and Attention Models for Simulating Urban Densification
    El Hajjar, S.
    Abdallah, F.
    Kassem, H.
    Omrani, H.
    SUSTAINABLE CITIES AND SOCIETY, 2023, 98
  • [8] Dilated Long Short-Term Attention For Chaotic Time Series Applications
    Alyousif, Fatimah J.
    Alkhaldi, Nora A.
    2022 IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS (IEEE EAIS 2022), 2022,
  • [9] Long- and short-term collaborative attention networks for sequential recommendation
    Yumin Dong
    Yongfu Zha
    Yongjian Zhang
    Xinji Zha
    The Journal of Supercomputing, 2023, 79 : 18375 - 18393
  • [10] Refocused Attention: Long Short-Term Rewards Guided Video Captioning
    Dong, Jiarong
    Gao, Ke
    Chen, Xiaokai
    Cao, Juan
    NEURAL PROCESSING LETTERS, 2020, 52 (02) : 935 - 948