PIP: prototypes-injected prompt for Federated Class Incremental Learning

Date

2024

Authors

Ma'sum, M.A.
Pratama, M.
Ramasamy, S.
Liu, L.
Habibullah, H.
Kowalczyk, R.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

CIKM ’24 Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024, pp.1670-1679

Statement of Responsibility

Conference Name

The 33rd ACM International Conference on Information and Knowledge Management (21 Oct 2024 - 25 Oct 2024 : Idaho, USA)

Abstract

Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Existing FCIL methods call for high communication costs and exemplars from previous classes. We propose a novel rehearsal-free method for FCIL named prototypes-injected prompt (PIP) that involves 3 main ideas: a) prototype injection on prompt learning, b) prototype augmentation, and c) weighted Gaussian aggregation on the server side. Our experiment result shows that the proposed method outperforms the current state of the arts (SOTAs) with a significant improvement (up to 33%) in CIFAR100, MiniImageNet, and TinyImageNet datasets. Our extensive analysis demonstrates the robustness of PIP in different task sizes, and the advantage of requiring smaller participating local clients, and smaller global rounds. For further study, source codes of PIP, baseline, and experimental logs are shared publicly in https://github.com/anwarmaxsum/PIP.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

License

Grant ID

Call number

Persistent link to this record