用图神经网络增强多目标优化的动态参数配置。
Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
- 构建目标空间的图结构，通过GNN学习状态表示。
- 在多个测试问题上超越传统与现有DRL方法的性能。
- 适配不同目标类型、规模及进化算法，泛化能力强。
深度强化学习（DRL）广泛用于动态算法配置，尤其在进化计算中，能随执行过程自适应调整参数。然而，将DRL应用于多目标组合优化（MOCO）问题的算法配置仍相对未被探索。本文提出一种基于图神经网络（GNN）的DRL方法，用于配置多目标进化算法。将动态算法配置建模为马尔可夫决策过程，以目标空间中的解收敛情况构建图结构，利用GNN学习节点嵌入以增强状态表征。在多种MOCO挑战上的实验表明，该方法在效果和适应性上优于传统及现有DRL方法。同时具备对目标类型、问题规模的良好泛化能力，并适用于不同的进化计算方法。
原文摘要 · Abstract (English)
Deep reinforcement learning (DRL) has been widely used for dynamic algorithm configuration, particularly in evolutionary computation, which benefits from the adaptive update of parameters during the algorithmic execution. However, applying DRL to algorithm configuration for multi-objective combinatorial optimization (MOCO) problems remains relatively unexplored. This paper presents a novel graph neural network (GNN) based DRL to configure multi-objective evolutionary algorithms. We model the dynamic algorithm configuration as a Markov decision process, representing the convergence of solutions in the objective space by a graph, with their embeddings learned by a GNN to enhance the state representation. Experiments on diverse MOCO challenges indicate that our method outperforms traditional and DRL-based algorithm configuration methods in terms of efficacy and adaptability. It also exhibits advantageous generalizability across objective types and problem sizes, and applicability to different evolutionary computation methods.
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。