A KG-Enhanced Multi-Graph Neural Network for Attentive Herb Recommendation

Traditional Chinese Medicine (TCM) has the longest clinical history in Asia and contributes a lot to health maintenance worldwide. An essential step during the TCM diagnostic process is syndrome induction, which comprehensively analyzes the symptoms and generates an overall summary of the symptoms. Given a set of symptoms, the existing herb recommenders aim to generate the corresponding herbs as a treatment by inducing the implicit syndrome representations based on TCM prescriptions. As different symptoms have various importance during the comprehensive consideration, we argue that treating the co-occurred symptoms equally to do syndrome induction in the previous studies will lead to the coarse-grained syndrome representation. In this paper, we bring the attention mechanism to model the syndrome induction process. Given a set of symptoms, we leverage an attention network to discriminate the symptom importance and adaptively fuse the symptom embeddings. Besides, we introduce a TCM knowledge graph to enrich the input corpus and improve the quality of representation learning. Further, we build a KG-enhanced Multi-Graph Neural Network architecture, which performs the attentive propagation to combine node feature and graph structural information. Extensive experimental results on two TCM data sets show that our proposed model has the outstanding performance over the state-of-the-arts.

Automated summary

Traditional Chinese Medicine (TCM) plays a significant role in global health maintenance. Syndrome induction, an important step in TCM diagnostic process, involves comprehensive analysis of symptoms to generate an overall summary. Existing herb recommenders face the challenge of coarse-grained syndrome representation by treating co-occurred symptoms equally. This paper proposes an attention mechanism to model the syndrome induction process, leveraging a TCM knowledge graph to enhance representation learning. The KG-enhanced Multi-Graph Neural Network architecture combines node feature and graph structural information through attentive propagation, achieving superior performance over existing models.