TY - GEN
T1 - Sequential Invariant Information Bottleneck
AU - Zhang, Yichen
AU - Yu, Shujian
AU - Chen, Badong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Previous approaches to the problem of generalization for out-of-distribution (OOD) data usually assume that data from each environment is available simultaneously, which is unrealistic in real-world applications. In this paper, we develop a new framework termed the sequential invariant information bottleneck (seq-IIB) to improve the generalization ability of learning agents in sequential environments. Our main idea is to combine the merits of the famed Information Bottleneck (IB) principle with the Invariant Risk Minimization (IRM), such that the learning agent can gradually remove spurious features and remain invariant and compact task-relevant information in a sequential manner. Experimental results on three MNIST-like datasets show the effectiveness of our method.
AB - Previous approaches to the problem of generalization for out-of-distribution (OOD) data usually assume that data from each environment is available simultaneously, which is unrealistic in real-world applications. In this paper, we develop a new framework termed the sequential invariant information bottleneck (seq-IIB) to improve the generalization ability of learning agents in sequential environments. Our main idea is to combine the merits of the famed Information Bottleneck (IB) principle with the Invariant Risk Minimization (IRM), such that the learning agent can gradually remove spurious features and remain invariant and compact task-relevant information in a sequential manner. Experimental results on three MNIST-like datasets show the effectiveness of our method.
KW - IRM
KW - Information Bottleneck
KW - Out-of-distribution generalization
KW - sequential environments
UR - https://www.scopus.com/pages/publications/85177603687
U2 - 10.1109/ICASSP49357.2023.10094563
DO - 10.1109/ICASSP49357.2023.10094563
M3 - 会议稿件
AN - SCOPUS:85177603687
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Y2 - 4 June 2023 through 10 June 2023
ER -