cs.AI updates on arXiv.org 12小时前
Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种超越检索的适配器重用框架,通过将适配器组合视为一个几何感知的稀疏重建问题,以提升参数高效的迁移学习性能。该框架在多个领域验证了其有效性,特别是医疗图像分割、医疗报告生成和图像合成任务。

arXiv:2410.09908v2 Announce Type: replace-cross Abstract: Recent advances in parameter-efficient transfer learning have demonstrated the utility of composing LoRA adapters from libraries of pretrained modules. However, most existing approaches rely on simple retrieval heuristics or uniform averaging, which overlook the latent structure of task relationships in representation space. We propose a new framework for adapter reuse that moves beyond retrieval, formulating adapter composition as a geometry-aware sparse reconstruction problem. Specifically, we represent each task by a latent prototype vector derived from the base model's encoder and aim to approximate the target task prototype as a sparse linear combination of retrieved reference prototypes, under an $\ell_1$-regularized optimization objective. The resulting combination weights are then used to blend the corresponding LoRA adapters, yielding a composite adapter tailored to the target task. This formulation not only preserves the local geometric structure of the task representation manifold, but also promotes interpretability and efficient reuse by selecting a minimal set of relevant adapters. We demonstrate the effectiveness of our approach across multiple domains-including medical image segmentation, medical report generation and image synthesis. Our results highlight the benefit of coupling retrieval with latent geometry-aware optimization for improved zero-shot generalization.

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

迁移学习 适配器重用 几何感知优化
相关文章