Multiple Modes for Continual Learning
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter subspace to remember old tasks, else drift away from the subspace and forget. From this observation, we formulate a trade-off between constructing multiple parameter modes and allocating tasks per mode. Mode-Optimized Task Allocation (MOTA), our contributed adaptation strategy, trains multiple modes in parallel, then optimizes task allocation per mode. We empirically demonstrate improvements over baseline continual learning strategies and across varying distribution shifts, namely sub-population, domain, and task shift.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Continual Learning of Multi-modal Dynamics with External Memory
We study the problem of fitting a model to a dynamical environment when new modes of behavior emerge sequentially. The learning model is aware when a new mode appears, but it cannot access the true modes of individual tr…
Continual LearningMode-Aware Continual Learning for Conditional Generative Adversarial Networks
The main challenge in continual learning for generative models is to effectively learn new target modes with limited samples while preserving previously learned ones. To this end, we introduce a new continual learning ap…
Continual LearningDeep Learning-Based Residual Useful Lifetime Prediction for Assets with Uncertain Failure Modes
Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple fa…
Deep LearningContinual Reasoning Gym: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes capability expansion costly. We therefore …
Reinforcement LearningVisual ReasoningDistributed Continual Learning
This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge. We introduce a mathematical frame…
Continual LearningFederated Learning