发表机构
University of Stirling（斯特林大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出在语义空间构建搜索轨迹网络（STN）的方法，通过离散化语义向量并聚类聚合到节点。应用于不同机器学习算法的任务及研究神经网络泛化，发现不同训练方式下STN结构有差异，能捕获学习算法与数据相互作用的训练动态，用于分析比较学习动态。
AI 中文摘要
搜索轨迹网络（STN）是一种基于图形的工具，用于可视化和表征优化算法的行为。STN对搜索空间离散化的依赖使其主要局限于低维或组合设置。我们引入了一种在语义空间中构建STN的方法，语义空间定义为模型在固定样本集上预测的空间。我们的方法离散化语义向量，并通过在归一化汉明距离下使用完全链接的凝聚聚类将它们聚合到网络节点中。由于任何预测器都可以由其语义向量概括，该方法能够比较不同算法家族之间的学习动态。我们将语义空间STN应用于使用不同机器学习算法解决的分类和回归任务，发现了它们之间已知的定性差异。此外，我们通过对比标准训练和Zhang等人（2017）的标签随机化机制来研究神经网络的泛化。结果表明，在真实标签上训练产生的STN比在随机标签上训练产生的图更密集、更高效和更集中。我们的结果表明，语义空间STN捕获了学习算法和数据之间相互作用产生的功能训练动态，为分析和比较机器学习模型和训练机制的学习动态提供了一种工具。
英文摘要
Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on discretization of the search space has largely confined them to low-dimensional or combinatorial settings. We introduce a methodology for constructing STNs in semantic spaces, defined as the space of a model's predictions on a fixed sample set. Our approach discretizes semantic vectors and aggregates them into network nodes via agglomerative clustering with complete linkage under a normalized Hamming distance. Since any predictor can be summarized by its semantic vector, this method enables comparison of learning dynamics across otherwise incomparable algorithm families. We apply semantic space STNs to classification and regression tasks solved using different machine learning algorithms, recovering known qualitative differences between them. Additionally, we use semantic space STNs to study neural network generalization by contrasting standard training with the label randomization regime of Zhang et al. (2017). The resulting STNs exhibit consistent structural differences, training on real labels produces denser, more efficient and more centralized graphs than training on shuffled labels. Together, our results show that semantic space STNs capture functional training dynamics arising from the interaction between learning algorithms and data, providing a tool for analyzing and comparing learning dynamics across machine learning models and training regimes.
Comments18 pages, 12 figures, submitted to EA 2026: 17th Biennal International Conference on Artificial Evolution
