Continual Learning is a burgeoning domain in next-generation AI, focusing on training neural networks over a sequence of tasks akin to human learning. While CL provides an edge over traditional supervised learning, its central challenge remains to counteract catastrophic forgetting and ensure the retention of prior tasks during subsequent learning. Amongst various strategies to tackle this, replay based methods have emerged as preeminent, echoing biological memory mechanisms. However, these methods are memory intensive, often preserving entire data samples, an approach inconsistent with humans selective memory retention of salient experiences. While some recent works have explored the storage of only significant portions of data in episodic memory, the inherent nature of partial data necessitates innovative retrieval mechanisms. Current solutions, like inpainting, approximate full data reconstruction from partial cues, a method that diverges from genuine human memory processes. Addressing these nuances, this paper presents the Saliency Guided Hidden Associative Replay for Continual Learning. This novel framework synergizes associative memory with replay-based strategies. SHARC primarily archives salient data segments via sparse memory encoding. Importantly, by harnessing associative memory paradigms, it introduces a content focused memory retrieval mechanism, promising swift and near-perfect recall, bringing CL a step closer to authentic human memory processes. Extensive experimental results demonstrate the effectiveness of our proposed method for various continual learning tasks.

翻译：摘要：持续学习作为下一代人工智能中的新兴领域，致力于模拟人类学习方式，在任务序列上训练神经网络。相较于传统监督学习，持续学习虽有优势，但其核心挑战仍在于克服灾难性遗忘，确保后续学习过程中对先前任务的记忆保持。在多种应对策略中，基于重放的方法因模拟生物记忆机制而脱颖而出。然而，这些方法存在高内存消耗问题——通常需完整保存数据样本，这与人类对显著经验的选择性记忆保留机制相悖。尽管近期研究探索了仅存储情景记忆中的数据关键部分，但部分数据的固有特性需要创新的检索机制。如修复补齐等现有解决方案通过部分线索近似重建完整数据，却偏离了真实的人类记忆过程。针对这些难点，本文提出基于显著性引导的隐式联想重放持续学习方法（SHARC）。该创新框架将联想记忆与重放策略深度融合：首先通过稀疏记忆编码存储显著数据片段，继而利用联想记忆范式建立内容聚焦的记忆检索机制，实现快速且近完美的记忆召回，使持续学习更接近真实人类记忆过程。大量实验结果表明，该方法在各类持续学习任务中均展现出显著成效。