论文标题
结构地标和相互作用建模：图形分类中的解决难题
Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
论文作者
论文摘要
图形神经网络是学习和推断图形结构数据的有希望的体系结构。然而，建模``零件''及其``交互式''的困难仍然存在于图形分类方面，在图形分类中，通常通过将整个图形挤压到单个向量中，通过图形池进行绘制。从复杂的系统的角度来看，将系统的所有部分混合在一起都会影响模型的解释性和预测性能，因为复杂系统的属性很大程度上是由于其组件之间的相互作用而产生的。我们通过学习理论恢复保证的统一概念在“解决难题”的统一概念下分析了图形分类的内在难度，并提出了``Slim''，这是一种用于结构地标和相互作用建模的电感神经网络模型。事实证明，通过解决分辨率的困境，并利用图表的组件部分之间的明确相互作用的关系来解释其复杂性，Slim更容易解释，准确，并在图表表示学习中提供了新的见解。
Graph neural networks are promising architecture for learning and inference with graph-structured data. Yet difficulties in modelling the ``parts'' and their ``interactions'' still persist in terms of graph classification, where graph-level representations are usually obtained by squeezing the whole graph into a single vector through graph pooling. From complex systems point of view, mixing all the parts of a system together can affect both model interpretability and predictive performance, because properties of a complex system arise largely from the interaction among its components. We analyze the intrinsic difficulty in graph classification under the unified concept of ``resolution dilemmas'' with learning theoretic recovery guarantees, and propose ``SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling. It turns out, that by solving the resolution dilemmas, and leveraging explicit interacting relation between component parts of a graph to explain its complexity, SLIM is more interpretable, accurate, and offers new insight in graph representation learning.
