Rethinking Transfer in Continual Learning: A Replay-Based Realisation
A new preprint introduces Transfer-Selective Replay (TSR), a method for continual learning that selectively replays past data predicted to benefit the current task, rather than replaying all past examples. TSR is guided by a task signature and uses distillation to maintain stability, showing improved forward transfer and outperforming existing replay baselines on both heterogeneous and homogeneous task streams.
Why it matters: This work reframes transfer as a primary objective in continual learning and provides both a theoretical framework and a practical method to achieve more effective transfer between tasks.
Full story at: arXiv Machine Learning ↗