Graph neural networks (GNNs) have led to major breakthroughs in a variety of
domains such as drug discovery, social network analysis, and travel time
estimation. However, they lack interpretability which hinders human trust and
thereby deployment to settings with high-stakes decisions. A line of
interpretable methods approach this by discovering a small set of relevant
concepts as subgraphs in the last GNN layer that together explain the
prediction. This can yield oversimplified explanations, failing to explain the
interaction between GNN layers. To address this oversight, we provide HELP
(Hierarchical Explainable Latent Pooling), a novel, inherently interpretable
graph pooling approach that reveals how concepts from different GNN layers
compose to new ones in later steps. HELP is more than 1-WL expressive and is
the first non-spectral, end-to-end-learnable, hierarchical graph pooling method
that can learn to pool a variable number of arbitrary connected components. We
empirically demonstrate that it performs on-par with standard GCNs and popular
pooling methods in terms of accuracy while yielding explanations that are
aligned with expert knowledge in the domains of chemistry and social networks.
In addition to a qualitative analysis, we employ concept completeness scores as
well as concept conformity, a novel metric to measure the noise in discovered
concepts, quantitatively verifying that the discovered concepts are
significantly easier to fully understand than those from previous work. Our
work represents a first step towards an understanding of graph neural networks
that goes beyond a set of concepts from the final layer and instead explains
the complex interplay of concepts on different levels.

提供 HELP (Hierarchical Explainable Latent Pooling) 这一新颖、本质上可解释的图汇聚方法，它揭示了不同图神经网络层次的概念如何组合成后续步骤中的新概念。通过定性分析和定量验证，我们证明了 HELP 在化学和社交网络领域的领域知识上与标准 GCN 和热门汇聚方法表现相当的准确性，同时提供了更易于理解的解释。这项工作代表了对图神经网络的理解迈出的第一步，超越了来自最终层次的一组概念，而是解释了不同层次概念之间的复杂相互作用。

Everybody Needs a Little HELP: 通过层次概念解释图形

Everybody Needs a Little HELP: Explaining Graphs via Hierarchical  Concepts

Graph neural networks get significant attention for graph representation and
classification in machine learning community. Attention mechanism applied on
the neighborhood of a node improves the performance of graph neural networks.
Typically, it helps to identify a neighbor node which plays more important role
to determine the label of the node under consideration. But in real world
scenarios, a particular subset of nodes together, but not the individual pairs
in the subset, may be important to determine the label of the graph. To address
this problem, we introduce the concept of subgraph attention for graphs. On the
other hand, hierarchical graph pooling has been shown to be promising in recent
literature. But due to noisy hierarchical structure of real world graphs, not
all the hierarchies of a graph play equal role for graph classification.
Towards this end, we propose a graph classification algorithm called
SubGattPool which jointly learns the subgraph attention and employs two
different types of hierarchical attention mechanisms to find the important
nodes in a hierarchy and the importance of individual hierarchies in a graph.
Experimental evaluation with different types of graph classification algorithms
shows that SubGattPool is able to improve the state-of-the-art or remains
competitive on multiple publicly available graph classification datasets. We
conduct further experiments on both synthetic and real world graph datasets to
justify the usefulness of different components of SubGattPool and to show its
consistent performance on other downstream tasks.

本研究提出了一种名为 SubGattPool 的算法，它能够联合学习子图注意力，利用两种不同类型的分层注意机制，以找到层次结构中的重要节点和图形中各层次结构的重要性，从而解决了现实世界中的图形分类问题，并在多个公开可用的图形分类数据集上取得了显著的性能提升。