用图神经网络指导遗传编程，提升符号回归效率。
Guiding Genetic Programming with Graph Neural Networks
- 先用图神经网络分析问题，生成子程序库
- 用生成的子程序库初始化种群并引导搜索
- 在多个问题上显著优于传统遗传编程方法
在进化计算中，通常假设搜索算法通过从搜索空间采样解并使用适应度函数评估来获取问题知识。然而，这种做法效率低下，因为适应度仅揭示少量信息——而解中其实蕴含更多可利用的潜在知识。针对遗传编程中的这一问题，我们提出EvoNUDGE，利用图神经网络从符号回归问题中提取额外知识。该网络在进化运行前对问题进行查询，生成一个子程序库，随后用于种子初始种群并引导搜索算子的行为。在大量问题实例上的广泛实验表明，EvoNUDGE显著优于多个基线方法，包括传统的树形遗传编程和纯神经变体。
原文摘要 · Abstract (English)
In evolutionary computation, it is commonly assumed that a search algorithm acquires knowledge about a problem instance by sampling solutions from the search space and evaluating them with a fitness function. This is necessarily inefficient because fitness reveals very little about solutions -- yet they contain more information that can be potentially exploited. To address this observation in genetic programming, we propose EvoNUDGE, which uses a graph neural network to elicit additional knowledge from symbolic regression problems. The network is queried on the problem before an evolutionary run to produce a library of subprograms, which is subsequently used to seed the initial population and bias the actions of search operators. In an extensive experiment on a large number of problem instances, EvoNUDGE is shown to significantly outperform multiple baselines, including the conventional tree-based genetic programming and the purely neural variant of the method.
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。