Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation.

从电信网络到量子化学，图形结构数据在自然科学和社会科学中无处不在。将关系归纳偏见构建到深度学习体系结构中对于创建能够从此类数据学习、推理和概括的系统至关重要。近年来，关于图表示学习的研究出现了激增，包括深度图嵌入技术、将卷积神经网络推广到图结构数据以及受信念传播启发的神经消息传递方法。