让进化算法参数随网络架构一起演化，自动调参并提升搜索效率。
Ecological Neural Architecture Search
- 将种群规模、变异率等参数编码进候选解，与网络结构共同进化。
- 在4个数据集上收敛速度提升18.3%，3个数据集准确率超越对比方法。
- 适合追求自动化、低资源消耗的神经网络架构搜索场景。
使用进化算法优化神经网络架构时，开发者还需手动调节种群大小、变异率、克隆率和迭代代数等超参数。本文提出神经生态型神经架构搜索（ENAS），将这些进化参数直接纳入候选解的表型中，使其与网络结构一同动态演化。在四个二分类数据集上的实验表明，ENAS不仅消除了对进化参数的手动调优，还显著提升了收敛速度（计算时间减少18.3%），并在3个数据集上取得更高分类精度。通过让‘贪婪个体’根据适应度动态分配资源，ENAS提供了一种高效且自调节的神经架构搜索方法。
原文摘要 · Abstract (English)
When employing an evolutionary algorithm to optimize a neural networks architecture, developers face the added challenge of tuning the evolutionary algorithm's own hyperparameters - population size, mutation rate, cloning rate, and number of generations. This paper introduces Neuvo Ecological Neural Architecture Search (ENAS), a novel method that incorporates these evolutionary parameters directly into the candidate solutions' phenotypes, allowing them to evolve dynamically alongside architecture specifications. Experimental results across four binary classification datasets demonstrate that ENAS not only eliminates manual tuning of evolutionary parameters but also outperforms competitor NAS methodologies in convergence speed (reducing computational time by 18.3%) and accuracy (improving classification performance in 3 out of 4 datasets). By enabling "greedy individuals" to optimize resource allocation based on fitness, ENAS provides an efficient, self-regulating approach to neural architecture search.
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。