Continuous molecular graph representations are highly useful for effective molecule property predictions. However, learning graph-specific structure information remains challenging. Current graph neural network models typically aggregate all node embeddings of a graph into a single vector, which, while being an efficient compressor, may not capture the high-level function-related substructure information, e.g., motifs. Moreover, the nodes that are loosely relevant to the graph representation may lead to the sub-optimal representation learning. Towards these limitations, in this paper we propose a new approach to enrich molecular graph representation, where the most relevant motif are selected to represent the graph at a high level and the key-node spanned subgraph is constructed to filter out irrelevant nodes. By comparing to recently proposed unimodal graph neural network models and multi-modal methods, we show that our method achieves state-of-the-art performance on molecular property prediction task.

MOTIVATION: Predicting the properties of molecules is a fundamental problem in drug design and discovery, while how to learn effective feature representations lies at the core of modern deep-learning-based prediction methods. Recent progress shows expressive power of graph neural networks (GNNs) in capturing structural information for molecular graphs. However, we find that most molecular graphs exhibit low clustering along with dominating chains. Such topological characteristics can induce feature squashing during message passing and thus impair the expressivity of conventional GNNs. RESULTS: Aiming at improving node features' expressiveness, we develop a novel chain-aware graph neural network model, wherein the chain structures are captured by learning the representation of the center node along the shortest paths starting from it, and the redundancy between layers are mitigated via initial residual difference connection (IRDC). Then the molecular graph is represented by attentive pooling of all node representations. Compared to standard graph convolution, our chain-aware learning scheme offers a more straightforward feature interaction between distant nodes, thus it is able to capture the information about long-range dependency. We provide extensive empirical analysis on real-world datasets to show the outperformance of the proposed method. AVAILABILITY AND IMPLEMENTATION: The MolPath code is publicly available at https://github.com/Assassinswhh/Molpath.

Graph representation learning aims at integrating node contents with graph structure to learn nodes/graph representations. Nevertheless, it is found that many existing graph learning methods do not work well on data with high heterophily level that accounts for a large proportion of edges between different class labels. Recent efforts to this problem focus on improving the message passing mechanism. However, it remains unclear whether heterophily truly does harm to the performance of graph neural networks (GNNs). The key is to unfold the relationship between a node and its immediate neighbors, e.g., are they heterophilous or homophilious? From this perspective, here we study the role of heterophily in graph representation learning before/after the relationships between connected nodes are disclosed. In particular, we propose an end-to-end framework that both learns the type of edges (i.e., heterophilous/homophilious) and leverage edge type information to improve the expressiveness of graph neural networks. We implement this framework in two different ways. Specifically, to avoid messages passing through heterophilous edges, we can optimize the graph structure to be homophilious by dropping heterophilous edges identified by an edge classifier. Alternatively, it is possible to exploit the information about the presence of heterophilous neighbors for feature learning, so a hybrid message passing approach is devised to aggregate homophilious neighbors and diversify heterophilous neighbors based on edge classification. Extensive experiments demonstrate the remarkable performance improvement of GNNs with the proposed framework on multiple datasets across the full spectrum of homophily level.

Multiple recent studies show a paradox in graph convolutional networks (GCNs)—that is, shallow architectures limit the capability of learning information from high-order neighbors, whereas deep architectures suffer from over-smoothing or over-squashing. To enjoy the simplicity of shallow architectures and overcome their limits of neighborhood extension, in this work we introduce a biaffine technique to improve the expressiveness of GCNs with a shallow architecture. The core design of our method is to learn direct dependency on long-distance neighbors for nodes, with which only 1-hop message passing is capable of capturing rich information for node representation. Besides, we propose a multi-view contrastive learning method to exploit the representations learned from long-distance dependencies. Extensive experiments on nine graph benchmark datasets suggest that the shallow biaffine graph convolutional networks (BAGCN) significantly outperform state-of-the-art GCNs (with deep or shallow architectures) on semi-supervised node classification. We further verify the effectiveness of biaffine design in node representation learning and the performance consistency on different sizes of training data.