Deakin University
Browse

File(s) under embargo

Class-incremental learning with causal relational replay

journal contribution
posted on 2024-05-09, 02:20 authored by T Nguyen, D Kieu, B Duong, T Kieu, Kien DoKien Do, Thin NguyenThin Nguyen, B Le
In Class-Incremental Learning (Class-IL), deep neural networks often fail to learn a sequence of classes incrementally due to catastrophic forgetting, a phenomenon arising from the absence of exposure to old knowledge. To alleviate this issue, conventional rehearsal methods, such as experience replay, store a limited number of old exemplars and then interleave with the current data for joint learning and rehearsal. However, the networks following this training scheme might not successfully reduce forgetting due to the lack of direct consideration of relations between samples of previously learned and new classes. Drawing inspiration from how humans learn by noticing the similarities and differences between classes, we propose a novel Class-IL framework called Relational Replay (RR). RR learns and recalls relations between images across all classes over time. To ensure these relations remain intrinsic and robust to forgetting, we incorporate causal reasoning to RR, resulting in Causal Relational Replay (CRR). CRR analyzes these relations using a causality perspective, aiming to identify intrinsic relations rooted in the images’ semantic features, serving as the cause of these relations. Our proposed method shows a competitive performance compared to the state-of-the-art rehearsal methods in Class-IL with clear and consistent improvements in the majority of settings on standard benchmark datasets.

History

Journal

Expert Systems with Applications

Volume

250

Article number

123901

Pagination

123901-123901

Location

Amsterdam, The Netherlands

ISSN

0957-4174

eISSN

1873-6793

Language

en

Publication classification

C1 Refereed article in a scholarly journal

Publisher

Elsevier BV

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC