English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning models often suffer from forgetting previously learnedinformation when trained on new data. This problem is exacerbated in federatedlearning (FL), where the data is distributed and can change independently foreach user. Many solutions are proposed to resolve this catastrophic forgettingin a centralized setting. However, they do not apply directly to FL because ofits unique complexities, such as privacy concerns and resource limitations. Toovercome these challenges, this paper presents a framework for$\textbf{federated class incremental learning}$ that utilizes a generativemodel to synthesize samples from past distributions. This data can be laterexploited alongside the training data to mitigate catastrophic forgetting. Topreserve privacy, the generative model is trained on the server using data-freemethods at the end of each task without requesting data from clients. Moreover,our solution does not demand the users to store old data or models, which givesthem the freedom to join/leave the training at any time. Additionally, weintroduce SuperImageNet, a new regrouping of the ImageNet dataset specificallytailored for federated continual learning. We demonstrate significantimprovements compared to existing baselines through extensive experiments onmultiple datasets.

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks