TY - GEN
T1 - MULTI-VIEW INFORMATION BOTTLENECK WITHOUT VARIATIONAL APPROXIMATION
AU - Zhang, Qi
AU - Yu, Shujian
AU - Xin, Jingmin
AU - Chen, Badong
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - By “intelligently” fuse the complementary information across different views, multi-view learning is able to improve the performance of classification task. In this work, we extend the information bottleneck principle to supervised multi-view learning scenario and use the recently proposed matrix-based Rényi's α-order entropy functional to optimize the resulting objective directly, without the necessity of variational approximation or adversarial training. Empirical results in both synthetic and real-world datasets suggest that our method enjoys improved robustness to noise and redundant information in each view, especially given limited training samples. Code is available at https://github.com/archy666/MEIB.
AB - By “intelligently” fuse the complementary information across different views, multi-view learning is able to improve the performance of classification task. In this work, we extend the information bottleneck principle to supervised multi-view learning scenario and use the recently proposed matrix-based Rényi's α-order entropy functional to optimize the resulting objective directly, without the necessity of variational approximation or adversarial training. Empirical results in both synthetic and real-world datasets suggest that our method enjoys improved robustness to noise and redundant information in each view, especially given limited training samples. Code is available at https://github.com/archy666/MEIB.
KW - Information bottleneck
KW - matrix-based Rényi's α-order entropy functional
KW - multi-view learning
UR - https://www.scopus.com/pages/publications/85131228323
U2 - 10.1109/ICASSP43922.2022.9747614
DO - 10.1109/ICASSP43922.2022.9747614
M3 - 会议稿件
AN - SCOPUS:85131228323
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4318
EP - 4322
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Y2 - 22 May 2022 through 27 May 2022
ER -