Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
This work addresses the problem of feature entanglement in continual learning for AI models, offering an incremental improvement with specific gains.
The paper tackles feature entanglement across tasks in continual learning by proposing Fresh-CL, which uses a dynamic mixture of experts on a hypersphere to enhance feature separation, achieving a 2% accuracy improvement over baselines on 11 datasets.
Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish between new domain data. In this work, we propose a method called Feature Realignment through Experts on hyperSpHere in Continual Learning (Fresh-CL). By leveraging predefined and fixed simplex equiangular tight frame (ETF) classifiers on a hypersphere, our model improves feature separation both intra and inter tasks. However, the projection to a simplex ETF shifts with new tasks, disrupting structured feature representation of previous tasks and degrading performance. Therefore, we propose a dynamic extension of ETF through mixture of experts, enabling adaptive projections onto diverse subspaces to enhance feature representation. Experiments on 11 datasets demonstrate a 2% improvement in accuracy compared to the strongest baseline, particularly in fine-grained datasets, confirming the efficacy of combining ETF and MoE to improve feature distinction in continual learning scenarios.