Federated continual learning improves task handling using relevance-based prompts
Task Relevance-Driven Prompt Expansion for Federated Continual Learning
Computer Vision and Pattern Recognition
Summary
It can be hard for computers working on many devices to learn new things over time without forgetting old knowledge, especially when they don’t know when new tasks will come or how many categories they include. The authors created a method that helps computers on each device detect when a new task arrives and figure out its size without prior info. They also developed a way to connect new tasks with related old tasks to learn better and avoid forgetting. Their approach was tested on various datasets and showed it can help computers learn continuously in a smarter way.
What this means in practice
- •For mobile app developers: Enable apps on user devices to learn new tasks continuously without needing prior info on task timing or size, improving personalization over time.
- •For iot system engineers: Improve devices in Internet of Things networks to detect and adapt to new tasks while reducing forgetting of old knowledge without central task scheduling.
Authors
Jiahua Dong, Wenqi Liang, Yang Cong, Yichen Li, Hongyuan Yu, Henghui Ding, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan
Abstract
Federated continual learning (FCL) has attracted considerable interest by enabling local clients to continually acquire knowledge from new tasks. However, most FCL methods assume that the global server has prior knowledge of the arrival times and number of categories for new tasks, which is unrealistic in the real world. Furthermore, they neglect the importance of positive inter-task semantic relationships when learning new tasks and are significantly affected by irrelevant relationships from old tasks, thereby exacerbating catastrophic forgetting. To resolve the above challenges, we develop a novel Task Relevance-driven Prompt Expansion (TRPE) model. Specifically, to eliminate the reliance on prior knowledge of new tasks, we propose an out-of-distribution detector to identify the arrival of new tasks within local clients, along with a radius-adaptive DBSCAN to infer the quantity of categories in new tasks on the proxy server. Moreover, to explore positive inter-task relationships, we calculate the affinity between the original gradient for learning new task and its gradient orthogonal to the feature space of old tasks to evaluate semantic relevance between old and new tasks from a global perspective. Then, we use this global task relevance to determine the key-prompt pair for new tasks and identify highly related old tasks. After concatenating their prompts for training, we can leverage such positive inter-task relations to improve the continual learning of newly arriving tasks. To balance the learning of new tasks and the forgetting of old ones, a soft orthogonality constraint is applied to the local key and prompt gradients. Experiments spanning diverse datasets and backbones confirm the efficacy of our TRPE model.