让AI Agent网络高效共享知识，降低通信与计算开销。
Distillation-Enabled Knowledge Alignment Protocol for Semantic Communication in AI Agent Networks
- 用知识蒸馏将各Agent专长转化为低秩矩阵，实现跨网络分配。
- 在仿真中相较传统方法显著降低通信与计算资源消耗。
- 适合需要多任务协同的AI网络系统，尤其关注资源效率的场景。
未来网络将连接海量人工智能（AI）代理，使其在多样化任务上广泛协作。与传统通信不同，这些代理天然适合语义通信（SC），可大幅提升带宽效率。然而，语义通信要求代理间知识对齐，而实际中各代理对其特定任务拥有独立专长知识。本文提出一种基于知识蒸馏的知识对齐协议（DeKAP），将每个代理的专家知识蒸馏为参数高效的低秩矩阵，在网络中分配，并使代理能同时保持对多个任务的知识对齐。我们将其联合优化对齐损失、通信开销和存储成本建模为大规模整数线性规划问题，并设计了一种高效贪心算法。计算机仿真表明，与传统方法相比，DeKAP以最低的通信与计算资源实现了知识对齐。
原文摘要 · Abstract (English)
Future networks are envisioned to connect massive artificial intelligence (AI) agents, enabling their extensive collaboration on diverse tasks. Compared to traditional entities, these agents naturally suit the semantic communication (SC), which can significantly enhance the bandwidth efficiency. Nevertheless, SC requires the knowledge among agents to be aligned, while agents have distinct expert knowledge for their individual tasks in practice. In this paper, we propose a distillation-enabled knowledge alignment protocol (DeKAP), which distills the expert knowledge of each agent into parameter-efficient low-rank matrices, allocates them across the network, and allows agents to simultaneously maintain aligned knowledge for multiple tasks. We formulate the joint minimization of alignment loss, communication overhead, and storage cost as a large-scale integer linear programming problem and develop a highly efficient greedy algorithm. From computer simulation, the DeKAP establishes knowledge alignment with the lowest communication and computation resources compared to conventional approaches.
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。