arXiv cs.AI· Nazim Abdeerhmane Aouni, Zakaria Soualah Mohammed, Maroua Ogab, Nour El Imane Elbar, Rayane Rahmat Errahmane Smara, Billel Moussous, Adriane Anis Khaled, Malika Bessedik, Fatima Benbouzid Si Tayeb, Hadjer Benmeziane·· 3 小时前AI 评分32
MOSHO：面向硬件感知神经架构搜索的原生离散鲨鱼启发元启发式算法
MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search
AI 导读
研究者提出 MOSHO（Multi-Objective Shark Hunting Optimization），一种用于硬件感知神经架构搜索（NAS）的原生离散元启发式算法，用离散架构编辑算子替代连续运动方程，以避免量化噪声。
正文 · 原文
Abstract:Hardware-aware neural architecture search (NAS) requires jointly optimizing predictive accuracy and device-specific latency over discrete search spaces. While multi-objective swarm optimizers show promise, continuous formulations such as the Multi-Objective White Shark Optimizer (MOWSO) can suffer from quantization noise when rounded to integer-encoded architecture vectors. To address this limitation, we propose MOSHO (Multi-Objective Shark Hunting Optimization), a native discrete metaheuristic that replaces continuous motion equations with discrete architecture-editing operators. MOSHO integrates adaptive operator scheduling, energy-regulated restarts, and deferred crowding-distance truncation to enhance exploration and search efficiency. On the merged NAS-Bench-201/HW-NAS-Bench benchmark across 18 contexts, MOSHO achieves a median normalized hypervolume of 0.9987 and IGD+ of 0.0064, yielding Pareto fronts competitive with NSGA-II while reducing search runtime by 96.4% (0.64 s vs. 17.72 s). These results demonstrate that tailored discrete search mechanisms can enable swarm optimizers to achieve high-quality multi-objective solution quality with substantially lower search cost in hardware-aware NAS.
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.33358 [cs.NE] |
| (or arXiv:2610.33358v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33358 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nazim Adeerhmane Aouni [view email]
[v1]
Fri, 23 Oct 2026 22:56:01 UTC (1,995 KB)
来源：arXiv cs.AI · arxiv.org