arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.15541cs.LGcs.NI
收藏

弥合局部与全局知识:用于近最短路径路由的级联专家混合学习

Bridging Local and Global Knowledge: Cascaded Mixture-of-Experts Learning for Near-Shortest Path Routing

The Ohio State University(俄亥俄州立大学)

Yung-Fu Chen, Anish Arora

AI总结:

本文提出级联混合专家模型,通过局部和全局特征结合提升稀疏网络路由性能,实验显示在稀疏网络中准确率提升29.1%,并保持不同密度网络中的高性能。

摘要:

尽管利用局部特征的深度学习模型在密集欧几里得图中表现出色,但在稀疏网络中泛化能力差,因拓扑不规则性需更广泛的结构意识。为此,我们训练了级联混合专家(Ca-MoE)解决所有对近最短路径(APNSP)路由问题。Ca-MoE是一种模块化的双层架构,下层专家依赖局部特征,上层专家依赖全局特征。它执行自适应推理,仅在下层专家无法达到足够决策质量时触发上层专家。通过按需提升模型容量,避免参数冗余。此外,我们引入在线元学习策略,实现专家独立微调,并利用以稳定性为导向的更新机制防止灾难性遗忘。实验表明,Ca-MoE路由在稀疏网络中比单专家基线提升29.1%的准确率,并在不同图密度下保持性能在理论上限的1%-6%范围内。

英文摘要:

While deep learning models that leverage local features have demonstrated significant potential for near-optimal routing in dense Euclidean graphs, they struggle to generalize well in sparse networks where topological irregularities require broader structural awareness. To address this limitation, we train a Cascaded Mixture of Experts (Ca-MoE) to solve the all-pairs near-shortest path (APNSP) routing problem. Our Ca-MoE is a modular two-tier architecture that supports the decision-making for forwarder selection with lower-tier experts relying on local features and upper-tier experts relying on global features. It performs adaptive inference wherein the upper-tier experts are triggered only when the lower-tier ones do not suffice to achieve adequate decision quality. Computational efficiency is thus achieved by escalating model capacity only when necessitated by topological complexity, and parameter redundancy is avoided. Furthermore, we incorporate an online meta-learning strategy that facilitates independent expert fine-tuning and utilizes a stability-focused update mechanism to prevent catastrophic forgetting as new graph environments are encountered. Experimental evaluations demonstrate that Ca-MoE routing improves accuracy by up to 29.1% in sparse networks compared to single-expert baselines and maintains performance within 1%-6% of the theoretical upper bound across diverse graph densities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑