克服自回归图生成中的顺序问题
Overcoming Order in Autoregressive Graph Generation
AI总结：
本文提出无序正则化（OLR）项，使RNN隐藏状态对图的不同有效顺序不变，以克服自回归图生成中的顺序问题，实验证明该方法在数据稀缺时尤其有效。
摘要：
图生成是包括化学和社会网络在内的多个领域中的一个基本问题。近期研究表明，与传统生成方法（需要将连续潜在表示转换为图）相比，使用循环神经网络（RNNs）进行分子图生成更具优势。当将图生成视为序列生成时，出现的一个问题是序列的任意顺序，这源于特定的图展平方法选择。在本工作中，我们提出使用RNNs，通过添加一个无序正则化（OLR）项来考虑图的非序列性质，该正则化项鼓励循环模型的隐藏状态对训练分布下存在的不同有效顺序保持不变。我们证明，序列图生成模型从我们提出的正则化方案中受益，尤其是在数据稀缺时。我们的发现为图生成研究领域的不断增长做出了贡献，并为需要合成真实且多样图结构的各种应用提供了有价值的工具。
英文摘要：
Graph generation is a fundamental problem in various domains, including chemistry and social networks. Recent work has shown that molecular graph generation using recurrent neural networks (RNNs) is advantageous compared to traditional generative approaches which require converting continuous latent representations into graphs. One issue which arises when treating graph generation as sequential generation is the arbitrary order of the sequence which results from a particular choice of graph flattening method. In this work we propose using RNNs, taking into account the non-sequential nature of graphs by adding an Orderless Regularization (OLR) term that encourages the hidden state of the recurrent model to be invariant to different valid orderings present under the training distribution. We demonstrate that sequential graph generation models benefit from our proposed regularization scheme, especially when data is scarce. Our findings contribute to the growing body of research on graph generation and provide a valuable tool for various applications requiring the synthesis of realistic and diverse graph structures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
