AI 中文总结
本研究针对无数据持续模型合并中预训练知识易被侵蚀的问题，提出SAFE-Merge框架，通过风险感知稀疏掩码与掩码低秩恢复实现最优H分数及最高准确率。
AI 中文摘要
无数据持续模型合并需在不访问任务数据的情况下，合并一系列专用模型，同时保留预训练通用知识和已习得任务。现有方法主要通过抑制下游任务间的干扰来合并任务更新，虽能保护已习得任务，但忽略了预训练知识本身的安全性，该知识的侵蚀会降低对未见过分布的泛化能力，并削弱未来任务获取的基础。我们提出SAFE-Merge，一种简单的无数据持续合并框架，其首先确定哪些参数更新可安全保留，随后恢复因掩码丢失的任务信息。具体而言，为确保安全性，风险感知稀疏掩码会选择携带任务特定信息且对通用知识风险较低的参数更新；掩码低秩恢复则仅使用相同保留的参数更新补偿丢失的任务信息，同时保持所有掩码参数严格不变；最终将合并后的更新融入主干，不产生额外推理成本。在视觉和语言基准上，SAFE-Merge始终取得最佳H分数；在更长的CLIP任务序列上，其较NUFILT大幅提升H分数，同时达到最高准确率。
英文摘要
Data-free continual model merging must incorporate a stream of specialized models while retaining both pretrained general knowledge and previously acquired tasks, without access to task data. Existing methods mainly merge task updates by suppressing interference among downstream tasks; while this protects previously acquired tasks, it overlooks the safety of the pretrained knowledge itself, whose erosion degrades generalization to held-out distributions and weakens the foundation for future task acquisition. We propose SAFE-Merge, a simple data-free continual-merging framework that first decides which parameter updates are safe to retain, and then recovers the task information lost through masking. Specifically, to ensure safety, risk-aware sparse masking selects parameter updates that carry task-specific information while posing low risk to general knowledge. Masked low-rank recovery then compensates for the lost task information using only the same retained parameter updates, while leaving all masked-out parameters strictly unchanged. Finally, the combined update is fused into the backbone, incurring no additional inference cost. Across vision and language benchmarks, SAFE-Merge consistently achieves the best H-score. On longer CLIP task sequences, it substantially improves H-score over NUFILT while also achieving the highest accuracy.
