<ul><li>Continual learning in deep neural networks often suffers from catastrophic forgetting, where representations for previous tasks are overwritten during subsequent training.</li><li>A novel sample retrieval strategy is proposed that leverages both gradient-conflicting and gradient-aligned samples to retain knowledge about past tasks.</li><li>Gradient-conflicting samples are selected to reduce interference and re-align gradients, preserving past task knowledge.</li><li>Experiments validate the method's state-of-the-art performance in mitigating forgetting and maintaining competitive accuracy on new tasks.</li></ul>

Balanced Gradient Sample Retrieval for Enhanced Knowledge Retention in Proxy-based Continual Learning

Discover more