ZAPS：用于神经架构搜索的零成本主动代理搜索
ZAPS: Zero-Cost Active Proxy Search for Neural Architecture Search
浏览论文内容
中文总结 AI 辅助
ZAPS提出四阶段零成本主动代理搜索流水线，结合抗冗余代理选择、混合K-means播种、自助投票重选及XGBoost集成，在NAS-Bench-201上以200次评估恢复超半数真实顶级架构，优于现有基线。
中文摘要 AI 辅助
神经架构搜索（NAS）自动化了网络设计，但评估单个候选架构需要将其训练至收敛，这使得穷举搜索变得不可行。零成本代理可在初始化时于数秒内估计架构质量，然而单一代理存在噪声，且组合多个代理并非直接有效：代理之间高度相关，因此朴素聚合会累积其共享误差而非将其平均抵消。现有方法要么利用代理信号，要么利用架构拓扑——从未在单一主动学习框架内同时利用两者。我们提出ZAPS（零成本主动代理搜索），这是一个四阶段流水线，填补了这一空白。ZAPS（i）通过ProxyFit（一种贪心抗冗余准则）离线选择紧凑且非冗余的代理子集；（ii）通过平衡利用与探索的混合K-means策略为搜索播种；（iii）随着标记集增长，在每次迭代中通过自助投票重新选择代理；（iv）使用在代理排名和独热拓扑编码上联合训练的XGBoost集成对候选进行排名，并通过上置信界（UCB）采集函数进行查询。在NAS-Bench-201上，在B=200次评估的预算下，ZAPS在CIFAR-10上恢复了真实前100架构中的52.3%，在CIFAR-100上恢复了65.8%，领先于我们考虑的所有基线——随机搜索、局部搜索、REA、BANANAS和TPE——并且在CIFAR-10上，其运行间标准差不到最强基线的一半。优势在评估稀缺时最为显著：在NAS-Bench-201上，随着预算增长优势缩小，而在更困难的NAS-Bench-101上（没有任何方法接近饱和），优势反而扩大。所有方法均通过单一标准评分：其实际评估的架构中有多少属于真实前100。
英文摘要
Neural Architecture Search (NAS) automates network design, but evaluating a single candidate requires training it to convergence, making exhaustive search intractable. Zero-cost proxies estimate architecture quality at initialization in seconds, yet a single proxy is noisy, and combining several does not straightforwardly help: proxies are strongly correlated, so naive aggregation compounds their shared errors instead of averaging them out. Existing methods exploit either proxy signals or architectural topology - never both within a single active-learning framework. We introduce ZAPS (Zero-cost Active Proxy Search), a four-stage pipeline that closes this gap. ZAPS (i) selects a compact, non-redundant proxy subset offline via ProxyFit, a greedy anti-redundancy criterion; (ii) seeds the search with a hybrid K-means strategy that balances exploitation and exploration; (iii) re-selects proxies at every iteration by a bootstrapped vote as the labeled set grows; and (iv) ranks candidates with an XGBoost ensemble trained jointly on proxy ranks and one-hot topological encodings, queried through an Upper Confidence Bound (UCB) acquisition function. On NAS-Bench-201 under a budget of B=200 evaluations, ZAPS recovers 52.3% of the true top-100 architectures on CIFAR-10 and 65.8% on CIFAR-100, ahead of every baseline we consider - Random Search, Local Search, REA, BANANAS and TPE - and, on CIFAR-10, with less than half the run-to-run standard deviation of the strongest of them. The advantage is largest where evaluations are scarce: on NAS-Bench-201 it narrows as the budget grows, whereas on the harder NAS-Bench-101, which no method comes close to saturating, it widens instead. All methods are scored by a single criterion: how much of the true top-100 lies among the architectures they actually evaluated.
发表机构
- ENSICAEN（卡昂国立高等工程师学校）
- ISIA Lab, Université de Mons（蒙斯大学ISIA实验室）
机构由 AI 辅助整理，请以论文原文为准。
