模块化delta融合与正交约束：一种可扩展的持续和可逆模型组合框架
Modular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition
AI总结：
本文提出MDM-OC框架，通过正交约束消除冲突，实现可扩展的持续和可逆模型组合，提升任务性能并满足合规需求。
摘要：
在现实世界机器学习部署中，模型必须持续更新、组合并在需要时选择性回滚。然而，现有模型融合和持续学习方法常面临任务干扰、灾难性遗忘或不可逆性问题。本文提出模块化delta融合与正交约束（MDM-OC）框架，通过将任务特定模型编码为共享基础的delta并投影到正交子空间以消除冲突，利用梯度优化合并delta形成统一模型，保持跨任务性能。该方法支持持续集成新模型、合规性回滚以及通过弹性权重整合和合成回放实现模型稳定性。在视觉和自然语言处理基准上的实验表明，MDM-OC在准确率、反向迁移和回滚保真度方面优于现有基线，同时保持内存高效和计算可行性。该框架为模块化和合规的AI系统设计提供了原理性解决方案。
英文摘要：
In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, existing approaches to model merging and continual learning often suffer from task interference, catastrophic forgetting, or lack of reversibility. We propose Modular Delta Merging with Orthogonal Constraints (MDM-OC), a novel framework that enables scalable, interference-free, and reversible composition of fine-tuned models. Each task-specific model is encoded as a delta from a shared base and projected into an orthogonal subspace to eliminate conflict. These projected deltas are then merged via gradient-based optimization to form a unified model that retains performance across tasks. Our approach supports continual integration of new models, structured unmerging for compliance such as GDPR requirements, and model stability via elastic weight consolidation and synthetic replay. Extensive experiments on vision and natural language processing benchmarks demonstrate that MDM-OC outperforms prior baselines in accuracy, backward transfer, and unmerge fidelity, while remaining memory-efficient and computationally tractable. This framework offers a principled solution for modular and compliant AI system design.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
