Autoencoder-Based Domain Learning for Semantic Communication with Conceptual Spaces

被引:0
|
作者
Wheeler, Dylan [1 ]
Natarajan, Balasubramaniam [1 ]
机构
[1] Kansas State Univ, Manhattan, KS 66506 USA
关键词
semantic communication; machine learning; conceptual spaces; autoencoder;
D O I
10.1109/WTS60164.2024.10536673
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Communication with the goal of accurately conveying meaning, rather than accurately transmitting symbols, has become an area of growing interest. This paradigm, termed semantic communication, typically leverages modern developments in artificial intelligence and machine learning to improve the efficiency and robustness of communication systems. However, a standard model for capturing and quantifying the details of "meaning" is lacking, with many leading approaches to semantic communication adopting a black-box framework with little understanding of what exactly the model is learning. One solution is to utilize the conceptual spaces framework, which models meaning explicitly in a geometric manner. Though prior work studying semantic communication with conceptual spaces has shown promising results, these previous attempts involve hand-crafting a conceptual space model, severely limiting the scalability and practicality of the approach. In this work, we develop a framework for learning a domain of a conceptual space model using only the raw data with high-level property labels. In experiments using the MNIST and CelebA datasets, we show that the domains learned using the framework maintain semantic similarity relations and possess interpretable dimensions.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] An autoencoder-based stacked LSTM transfer learning model for EC forecasting
    Abdullahi Uwaisu Muhammad
    Hamza Djigal
    Tasiu Muazu
    Jibril Muhammad Adam
    Abdoul Fatakhou Ba
    Umar Sani Dabai
    Sani Tijjani
    Muhammad Sabo Yahaya
    Aliyu Ashiru
    Umar Muhammad Mustapha Kumshe
    Saddam Aliyu
    Faruwa Ajibola Richard
    Earth Science Informatics, 2023, 16 : 3369 - 3385
  • [42] A Variational Autoencoder-Based Secure Transceiver Design Using Deep Learning
    Lin, Chia-Hung
    Wu, Chao-Chin
    Chen, Kuan-Fu
    Lee, Ta-Sung
    2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2020,
  • [43] Autoencoder-based composite drought indices
    Lee, Taesam
    Kong, Yejin
    Singh, Vijay
    Lee, Joo-Heon
    ENVIRONMENTAL RESEARCH LETTERS, 2024, 19 (07):
  • [44] An autoencoder-based spectral clustering algorithm
    Xinning Li
    Xiaoxiao Zhao
    Derun Chu
    Zhiping Zhou
    Soft Computing, 2020, 24 : 1661 - 1671
  • [45] A survey of autoencoder-based recommender systems
    Guijuan Zhang
    Yang Liu
    Xiaoning Jin
    Frontiers of Computer Science, 2020, 14 : 430 - 450
  • [46] Autoencoder-based Intrusion Detection System
    Kamalov, Firuz
    Zgheib, Rita
    Leung, Ho Hon
    Al-Gindy, Ahmed
    Moussa, Sherif
    2021 7TH INTERNATIONAL CONFERENCE ON ENGINEERING AND EMERGING TECHNOLOGIES (ICEET 2021), 2021, : 707 - 711
  • [47] A survey of autoencoder-based recommender systems
    Zhang, Guijuan
    Liu, Yang
    Jin, Xiaoning
    FRONTIERS OF COMPUTER SCIENCE, 2020, 14 (02) : 430 - 450
  • [48] Autoencoder-based unsupervised clustering and hashing
    Zhang, Bolin
    Qian, Jiangbo
    APPLIED INTELLIGENCE, 2021, 51 (01) : 493 - 505
  • [49] Autoencoder-based unsupervised clustering and hashing
    Bolin Zhang
    Jiangbo Qian
    Applied Intelligence, 2021, 51 : 493 - 505
  • [50] An autoencoder-based snow drought index
    Sinan Rasiya Koya
    Kanak Kanti Kar
    Shivendra Srivastava
    Tsegaye Tadesse
    Mark Svoboda
    Tirthankar Roy
    Scientific Reports, 13