用图语法生成满足复杂约束的图，解决传统方法长程依赖建模不足问题。
Learning to generate feasible graphs using graph grammars
- 基于图语法与领域自适应粗化，增强长程依赖建模能力
- 在分子图生成中达到MOSES基准优秀水平，药物相似性高
- 可生成含数百节点的有效RNA结构，通过顶级分类器验证
图生成方法需在建模节点间复杂依赖的同时满足特定领域的可行性约束（如原子键数过大会使分子无效）。现有基于消息传递的神经网络方法存在信息稀释问题，难以捕捉长程依赖。本文提出一种基于图语法的生成框架，引入领域相关的粗化机制，为长程依赖提供捷径。在小分子药物和RNA二级结构两个领域验证：小分子方面，使用MOSES基准评估生成分子的理化性质、合成性和类药性；在RNA方面，生成的大型图（数百节点）能被Infernal协方差模型识别为有效结构。代码已开源。
原文摘要 · Abstract (English)
Generative methods for graphs need to be sufficiently flexible to model complex dependencies between sets of nodes. At the same time, the generated graphs need to satisfy domain-dependent feasibility conditions, that is, they should not violate certain constraints that would make their interpretation impossible within the given application domain (e.g. a molecular graph where an atom has a very large number of chemical bounds). Crucially, constraints can involve not only local but also long-range dependencies: for example, the maximal length of a cycle can be bounded. Currently, a large class of generative approaches for graphs, such as methods based on artificial neural networks, is based on message passing schemes. These approaches suffer from information 'dilution' issues that severely limit the maximal range of the dependencies that can be modeled. To address this problem, we propose a generative approach based on the notion of graph grammars. The key novel idea is to introduce a domain-dependent coarsening procedure to provide short-cuts for long-range dependencies. We show the effectiveness of our proposal in two domains: 1) small drugs and 2) RNA secondary structures. In the first case, we compare the quality of the generated molecular graphs via the Molecular Sets (MOSES) benchmark suite, which evaluates the distance between generated and real molecules, their lipophilicity, synthesizability, and drug-likeness. In the second case, we show that the approach can generate very large graphs (with hundreds of nodes) that are accepted as valid examples for a desired RNA family by the "Infernal" covariance model, a state-of-the-art RNA classifier. Our implementation is available on github: github.com/fabriziocosta/GraphLearn
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。