Sequential Invariant Information Bottleneck

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728163277
DOIs
StatePublished - 2023
Event48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 202310 Jun 2023

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2023-June
ISSN (Print)1520-6149

Conference

Conference48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Country/TerritoryGreece
CityRhodes Island
Period4/06/2310/06/23

Keywords

  • IRM
  • Information Bottleneck
  • Out-of-distribution generalization
  • sequential environments

Fingerprint

Dive into the research topics of 'Sequential Invariant Information Bottleneck'. Together they form a unique fingerprint.

Cite this