cs.AI updates on arXiv.org 3小时前
MoKA: Mixture of Kronecker Adapters
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出MoKA,一种基于克罗内克积的参数高效微调方法,通过混合权重更新和门控机制,提升模型表达能力,实现参数效率和准确性的平衡。

arXiv:2508.03527v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is essential for reducing the computational overhead of large language models (LLMs). Low-rank family adapters are commonly used to control the parameter size efficiently while maintaining the generative power of LLMs. However, their limited expressiveness due to the rank constraint often restricts their performance on complex tasks. We propose Mixture of Kronecker Adapters (MoKA), a new generation of Kronecker adapters that addresses this limitation by modeling weight updates as a mixture of Kronecker products. Our proposed adapter leverages a gating mechanism that measures the importance of each Kronecker factor, enabling more expressive adaptation. Moreover, MoKA enables a rank flexibility that provides a better trade-off between parameter efficiency and accuracy. To ensure hardware efficiency, we reformulate Kronecker computations using standard matrix operations, allowing seamless deployment on GPU-optimized hardware. We conduct extensive experiments on instruction-tuning and commonsense reasoning tasks using low-bit quantized versions of LLaMA2-7B and LLaMA3-8B models. MoKA not only outperforms PEFT baselines, but also reduces the number of trainable parameters up to 27x, achieving state-of-the-art trade-offs between performance and parameter efficiency.

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

参数高效微调 克罗内克积 MoKA 模型表达能力 参数效率
相关文章