Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy. EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

翻译：持续学习旨在解决模型在连续任务训练中的灾难性遗忘问题。常用方法经验回放虽能存储历史样本，但仅能稀疏近似数据分布，导致决策边界脆弱且过度简化。为克服这一局限，我们提出支持边界数据（SBD）方法——通过差分隐私启发式噪声注入潜层特征，生成邻近决策边界的表征，从而隐式正则化决策边界。基于此思想，我们构建经验混合（EB）框架，采用双模型聚合策略联合训练历史样本与SBD。EB包含两个核心组件：(1) 潜层空间噪声注入生成支持边界数据；(2) 端到端训练联合利用历史样本与SBD。与标准经验回放不同，SBD有效丰富了决策边界的特征空间，使持续学习更加稳定鲁棒。在CIFAR-10、CIFAR-100、Tiny ImageNet和ImageNet1K数据集上的大量实验表明，准确率分别稳定提升10%、6%、13%和2%。