GaTaP：通过门控目标传播实现持续学习中的组合泛化
Gated Target Propagation for Compositional Generalization in Continual Learning
一篇持续学习论文，提出 GaTaP 算法，用门控机制既防遗忘又能 few-shot 学新任务组合，实验覆盖 MLP 和 CNN。
论文提出 Gated Target Propagation（GaTaP）持续学习算法，通过闭式内循环更新学习的任务特定门控变量来选择性抑制或增强网络模块。参数在较慢时间尺度的外循环中学习，使用与门控适应相同的局部 difference target propagation 误差信号。在 MLP 与卷积网络的 class-incremental learning 实验中，GaTaP 在已学任务上保持较强性能，并可通过推理时的 few-shot 增益适应泛化到未见过的任务组合。分析显示相关任务呈现相似门控模式，说明门控捕捉了可复用的任务结构。
Gated Target Propagation for Compositional Generalization in Continual Learning
Continual learning is typically framed as acquiring new knowledge without catastrophically forgetting previous tasks. However, a flexible continual learner should also be able to reuse and recombine previously acquired knowledge to rapidly solve novel task compositions. We introduce Gated Target Propagation (GaTaP), a continual learning algorithm in which task-specific gating variables---learned through a closed-form inner loop update---selectively suppress or enhance network modules. Network parameters are learned in a slower timescale outer loop, using the same local difference target propagation error signal as is used for adapting gating variables. We provide tractable experiments on class-incremental learning scenarios for both multilayer perceptron and convolutional network architectures. We show strong performance retention on previously learned tasks, as well as compositional generalization to unseen tasks, achieved through few-shot gain adaptation at inference. We analyze learned gating patterns and find that related tasks exhibit similar gating patterns, suggesting that inferred gates capture meaningful, reusable task structure. Overall, GaTaP provides a powerful framework for jointly ameliorating catastrophic forgetting and enabling few-shot compositional generalization in neural network models.
