.png){kind=icon}
Return
Deep Class-Incremental Learning From Decentralized Data
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3214573.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this article, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories. We initiate the study of data-decentralized class-incremental learning (DCIL) by making the following contributions. First, we formulate the DCIL problem and develop the experimental protocol. Second, we introduce a paradigm to create a basic decentralized counterpart of typical (centralized) CIL approaches, and as a result, establish a benchmark for the DCIL study. Third, we further propose a decentralized composite knowledge incremental distillation (DCID) framework to transfer knowledge from historical models and multiple local sites to the general model continually. DCID consists of three main components, namely, local CIL, collaborated knowledge distillation (KD) among local models, and aggregated KD from local models to the general one. We comprehensively investigate our DCID framework by using a different implementation of the three components. Extensive experimental results demonstrate the effectiveness of our DCID framework. The source code of the baseline methods and the proposed DCIL is available at https://github.com/Vision-Intelligence-and-Robots-Group/DCIL.
Keywords:
Data models
Adaptation models
Computational modeling
Training
Task analysis
Deep learning
Servers
Catastrophic forgetting
continuous learning
incremental learning (IL)
knowledge distillation (KD)
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSave
View more