抽象化：持续学习中的记忆高效归纳偏置

摘要

现实世界具有非平稳性与无限复杂性，智能体需要持续学习而无需承担从头训练的过高成本。虽然在线持续学习为此提供了框架，但新知识的学习往往会干扰已掌握知识，导致遗忘与泛化能力下降。为此，我们提出抽象增强训练（AAT），通过损失函数层面的改进促使模型捕捉样本间潜在的关联结构。通过联合优化具体实例及其抽象表征，AAT引入了一种内存高效的归纳偏置，能在严格在线数据流中稳定学习过程，无需使用回放缓冲区。为捕捉抽象的多维特性，我们在两个基准测试中引入并评估AAT：一是通过实体掩码实现抽象的可控关系数据集，二是通过共享谚语表达抽象的叙事数据集。实验结果表明，AAT在零额外内存开销且仅对训练目标做最小改动的情况下，取得了媲美甚至超越强经验回放（ER）基线的性能。这项工作揭示了结构抽象可作为ER的一种高效无内存替代方案。

English

The real world is non-stationary and infinitely complex, requiring intelligent agents to learn continually without the prohibitive cost of retraining from scratch. While online continual learning offers a framework for this setting, learning new information often interferes with previously acquired knowledge, causes forgetting and degraded generalization. To address this, we propose Abstraction-Augmented Training (AAT), a loss-level modification encouraging models to capture the latent relational structure shared across examples. By jointly optimizing over concrete instances and their abstract representations, AAT introduces a memory-efficient inductive bias that stabilizes learning in strictly online data streams, eliminating the need for a replay buffer. To capture the multi-faceted nature of abstraction, we introduce and evaluate AAT on two benchmarks: a controlled relational dataset where abstraction is realized through entity masking, and a narrative dataset where abstraction is expressed through shared proverbs. Our results show that AAT achieves performance comparable to or exceeding strong experience replay (ER) baselines, despite requiring zero additional memory and only minimal changes to the training objective. This work highlights structural abstraction as a powerful, memory-free alternative to ER.

抽象化：持续学习中的记忆高效归纳偏置

Abstraction as a Memory-Efficient Inductive Bias for Continual Learning

摘要

Support