无需训练即可高效安全地选择最适合的LoRA模型。
SEQR: Secure and Efficient QR-based LoRA Routing
- 基于激活范数最大化设计无监督路由算法
- 比现有方法更高效，能准确识别最优LoRA适配器
- 适合需要隐私保护的多任务动态部署场景
低秩适应（LoRA）已成为大语言模型参数高效微调的标准技术，支持为不同任务或领域构建大型LoRA库。在安全环境中，如何高效选择对应输入的正确LoRA适配器仍具挑战性，尤其当依赖有监督路由器训练时可能引发隐私问题。受先前方法启发，我们形式化了无监督LoRA路由的目标——通过最大化激活范数提供理论分析框架。实验表明激活范数具有强区分能力，并提出SEQR算法，旨在最大化效率并提供严格的路由保证。SEQR可证明性地以显著更高的效率识别范数最大化的适配器，是动态LoRA组合中高度可扩展且有效的解决方案。实验验证了其在多任务性能与效率上的提升。
原文摘要 · Abstract (English)
Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter for a given input remains a challenge, particularly in secure environments where supervised training of routers may raise privacy concerns. Motivated by previous approaches, we formalize the goal of unsupervised LoRA routing in terms of activation norm maximization, providing a theoretical framework for analysis. We demonstrate the discriminative power of activation norms and introduce SEQR, an unsupervised LoRA routing algorithm designed to maximize efficiency while providing strict routing guarantees. SEQR provably identifies the norm-maximizing adapter with significantly greater efficiency, making it a highly scalable and effective solution for dynamic LoRA composition. We validate our results through experiments that demonstrate improved multi-task performance and efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。