cs.AI updates on arXiv.org 07月29日 12:22
Modular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出了一种新型框架MDM-OC,用于实现机器学习模型的可扩展、无干扰和可逆组合,有效解决现有方法的干扰、遗忘和不可逆问题,并通过实验证明其在准确度、反向迁移和模型稳定性方面优于现有基准。

arXiv:2507.20997v1 Announce Type: cross Abstract: 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.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

机器学习 模型合并 持续学习 MDM-OC框架
相关文章