Exemplar-condensed Federated Class-incremental Learning

2024-12-25 · Rui Sun, Yumin Zhang, Varun Ojha, Tejal Shah, Haoran Duan, Bo Wei, Rajiv Ranjan

We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related to the heterogeneity of information density of each summarized data. Our approach maintains the consistency of training gradients and the relationship to past tasks for the summarized exemplars to represent the streaming data compared to the original images effectively. Additionally, our approach reduces the information-level heterogeneity of the summarized data by inter-client sharing of the disentanglement generative model. Extensive experiments show that our ECoral outperforms several state-of-the-art methods and can be seamlessly integrated with many existing approaches to enhance performance.

📄 PDF Abstract BibTeX arXiv:2412.18926

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning Continual Learning Disentanglement Incremental Learning

FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

2026-03-30 · Tiantian Wang, Xiang Xiang, Simon S. Du arxiv

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, …

class-incremental learning Continual Learning

Condensed Prototype Replay for Class Incremental Learning

2023-05-25 · Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, Huajie Shao

Incremental learning (IL) suffers from catastrophic forgetting of old tasks when learning new tasks. This can be addressed by replaying previous tasks' data stored in a memory, which however is usually prone to size limi…

class-incremental learning Class Incremental Learning Incremental Learning

Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

2025-01-26 · Milad Khademi Nori, Il-Min Kim, Guanghui Wang

Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forget…

class-incremental learning Class Incremental Learning Decoder Incremental Learning

PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark

2023-04-13 · Shivanand Kundargi, Tejas Anvekar, Ramesh Ashok Tabib, Uma Mudenagudi

Point clouds offer comprehensive and precise data regarding the contour and configuration of objects. Employing such geometric and topological 3D information of objects in class incremental learning can aid endless appli…

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning

Federated Class-Incremental Learning with Prompting

2023-10-13 · Jiale Liu, Yu-Wei Zhan, Chong-Yu Zhang, Xin Luo 외

As Web technology continues to develop, it has become increasingly common to use data stored on different clients. At the same time, federated learning has received widespread attention due to its ability to protect data…

class-incremental learning Class Incremental Learning Federated Learning Incremental Learning