Improving TCM Prescription Recommendation with Diffusion and Asymmetric Loss

Traditional Chinese Medicine (TCM) utilizes syndrome differentiation to formulate effective herbal prescriptions for treating complex diseases. Recently, some methods leveraging knowledge graph embedding and graph neural networks have shown promising performance. However, these approaches still straggle with challenges related to data quality, including sparsity and noise in knowledge graphs, as well as imbalances between positive and negative samples in datasets, which hinder performance improvements. To address these issues, our study introduces a novel approach integrating the Diffusion-Augmented Knowledge Graph Embedding and Graph Convolutional Network (GCN) with Asymmetric Loss (ASL). Firstly, we enhance herb representation by combining the Diffusion model with knowledge graph embedding to effectively mitigate noise and sparsity issues inherent in the knowledge graph. Then, we construct a TCM symptom-herb bipartite graph based on the dataset and employ a two-layer Bipartite Graph Convolutional Neural Network (Bipar GCN) to obtain feature embeddings. To tackle the imbalance between positive and negative samples, we introduce ASL to optimize the model. Finally, we aggregate symptom embeddings using MLP to derive a syndrome embedding, which is then multiplied with herb embeddings to compute prediction scores. Evaluated on a TCM prescription benchmark, our method outperforms others in Precision, Recall, and NDCG metrics, marking significant improvements in TCM prescription recommendation.