PIP: prototypes-injected prompt for Federated Class Incremental Learning
Files
(Published version)
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.