An Efficient and Accurate GPU-based Deep Learning Model for Multimedia Recommendation

被引:1
|
作者
Djenouri, Youcef [1 ]
Belhadi, Asma [2 ]
Srivastava, Gautam [3 ,4 ]
Lin, Jerry Chun-Wei [5 ]
机构
[1] SINTEF, SINTEF Digital, Forskningsveien 1, N-0373 Oslo, Norway
[2] Prinsens Gate 7-9, N-0107 Oslo, Norway
[3] Brandon Univ, Dept Math & Comp Sci, 270 18th St, Brandon, MB R7A 6A9, Canada
[4] China Med Univ, Res Ctr Interneural Comp, 91 Xueshi Rd, Taichung 40402, Taiwan
[5] Western Norway Univ Appl Sci, Dept Comp Sci Elect Engn & Math Sci, Inndalsveien 28, N-5063 Bergen, Norway
关键词
Human computer interaction; XAI; deep learning; GPU; pattern recommendation; multimedia data;
D O I
10.1145/3524022
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This article proposes the use of deep learning in human-computer interaction and presents a new explainable hybrid framework for recommending relevant hashtags on a set of orpheline tweets, which are tweets with hashtags. The approach starts by determining the set of batches used in the convolution neural network based on frequent pattern mining solutions. The convolutional neural network is then applied to the set of batches of tweets to learn the hashtags of the tweets. An optimization strategy has been proposed to accurately perform the learning process by reducing the number of frequent patterns. Moreover, eXplainable AI is introduced for hashtag recommendations by analyzing the user preferences and understanding the different weights of the deep learning model used in the learning process. This is performed by learning the hyper-parameters of the deep architecture using the genetic algorithm. GPU computing is also investigated to achieve high speed and enable the execution of the overall framework in real time. Extensive experimental analysis has been performed to show that our methodology is useful on different collections of tweets. The experimental results clearly show the efficiency of our proposed approach compared to baseline approaches in terms of both runtime and accuracy. Thus, the proposed solution achieves an accuracy of 90% when analyzing complex Wikipedia data while the other algorithms did not achieve 85% when processing the same amount of data.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] A Performance Estimation Model for GPU-Based Systems
    Issa, Joseph
    Figueira, Silvia
    2012 2ND INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTATIONAL TOOLS FOR ENGINEERING APPLICATIONS (ACTEA), 2012, : 279 - 283
  • [42] An Improved GPU-Based SAT Model Counter
    Fichte, Johannes K.
    Hecher, Markus
    Zisser, Markus
    PRINCIPLES AND PRACTICE OF CONSTRAINT PROGRAMMING, CP 2019, 2019, 11802 : 491 - 509
  • [43] GPUCSL: GPU-Based Library for Causal Structure Learning
    Braun, Tom
    Hurdelhey, Ben
    Meier, Dominik
    Tsayun, Petr
    2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW, 2022, : 1236 - 1239
  • [44] Fast and accurate line detection with GPU-based least median of squares
    Gil Shapira
    Tal Hassner
    Journal of Real-Time Image Processing, 2020, 17 : 839 - 851
  • [45] Fast and accurate line detection with GPU-based least median of squares
    Shapira, Gil
    Hassner, Tal
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2020, 17 (04) : 839 - 851
  • [46] An effective recommendation model based on deep representation learning
    Ni, Juan
    Huang, Zhenhua
    Cheng, Jiujun
    Gao, Shangce
    Information Sciences, 2021, 542 : 324 - 342
  • [47] An effective recommendation model based on deep representation learning
    Ni, Juan
    Huang, Zhenhua
    Cheng, Jiujun
    Gao, Shangce
    INFORMATION SCIENCES, 2021, 542 : 324 - 342
  • [48] Accurate and Efficient CPU/GPU-Based 3-DOF Haptic Rendering of Complex Static Virtual Environments
    Kim, Jong-Phil
    Lee, Beom-Chan
    Kim, Hyungon
    Kim, Jaeha
    Ryu, Jeha
    PRESENCE-TELEOPERATORS AND VIRTUAL ENVIRONMENTS, 2009, 18 (05) : 340 - 360
  • [49] EGraph: Efficient Concurrent GPU-Based Dynamic Graph Processing
    Zhang, Yu
    Liang, Yuxuan
    Zhao, Jin
    Mao, Fubing
    Gu, Lin
    Liao, Xiaofei
    Jin, Hai
    Liu, Haikun
    Guo, Song
    Zeng, Yangqing
    Hu, Hang
    Li, Chen
    Zhang, Ji
    Wang, Biao
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (06) : 5823 - 5836
  • [50] Efficient, GPU-Based 2D Mesh Smoothing
    Dahal, Sangeet
    Newman, Timothy S.
    IEEE SOUTHEASTCON 2014, 2014,