Search

Sequential recommendation is the mainstream approach in the field of click-through-rate (CTR) prediction for modeling users' behavior. This behavior implies the change of the user's interest, and the goal of sequential recommendation is to capture this dynamic change. However, existing studies have focused on designing complex dedicated networks to capture user interests from user behavior sequences, while neglecting the use of auxiliary information. Recently, knowledge graph (KG) has gradually attracted the attention of researchers as a structured auxiliary information. Items and their attributes in the recommendation, can be mapped to knowledge triples in the KG. Therefore, the introduction of KG to recommendation can help us obtain more expressive item representations. Since KG can be considered a special type of graph, it is possible to use the graph neural network (GNN) to propagate the rich information contained in the KG into the item representation. Based on this idea, this paper proposes a recommendation method that uses KG as auxiliary information. The method first propagates the knowledge information in the KG using GNN to obtain a knowledge-rich item representation. Then the temporal features in the item sequence are extracted using a transformer for CTR prediction, namely the Knowledge Graph-aware Deep Interest Extraction network (KGDIE). To evaluate the performance of this model, we conducted extensive experiments on two real datasets with different scenarios. The results showed that the KGDIE method could outperform several state-of-the-art baselines.

Background: Biliary Atresia (BA) is a devastating pediatric cholangiopathy affecting the bile ducts of the liver. Current research has found a variety of causes for BA, with inflammation and fibrosis is more studied. However, these etiological mechanisms are not present in all patients. Pyroptosis has been increasingly appreciated as a programmed cell death process but is less studied in BA. We have re-classified BA by integrating gene microarray data and scRNA-seq data to support individualized clinical treatment and mechanistic studies. Methods: The BA microarray dataset GSE122340 was downloaded from the Gene Expression Omnibus (GEO) database. GSE46960 and GSE15235 and sequencing data of identical twins as validation cohorts. Through retrospective analysis, 17 differential pyroptosis genes (DEPRGs) were used for typing research. An effective method for identifying BA typing through machine learning algorithms. Subsequently, we performed drug prediction for the pyroptosis subtype to enable individualized treatment. Pyroptosis-score was constructed and combined with scRNA-seq datasets to reveal immune cells and pathways activated during pyroptosis. Results: Two novel subtypes of pyroptosis were identified. The C1 subtype shows activation of pyroptosis, enhanced inflammatory response, and increased infiltration of monocytes and neutrophils. The C2 subtype exhibits cell cycle activation, low pyroptosis, and a milder inflammatory response. Macrophage pyroptosis may promote the infiltration of more immune cells and the release of inflammatory factors, further aggravating the occurrence of hepatic pyroptosis, which in turn leads to a poorer prognosis in inflammatory BA. Conclusion: In summary, we have defined two novel subtypes of pyroptosis and offered the possibility of identifying them and individualizing treatment. The role of macrophages, neutrophils, and plasma cells in the pyroptosis process of BA is worthy of further study.

The application of a graph convolutional network (GCN) to collaborative filtering (CF) is a new direction of recommendation system and has achieved good results. However, the problem of data uniformity, that is, the quality of embedded expression of different data after multiple convolutions, still persists. In this paper, we propose a convolution method using dense connection, which can effectively reduce data uniformity and improve the performance of the recommended model. This dense connection embedding calculation method can maximize the influence of low-order embedding on high-order embedding, thereby improving the uniformity of higher-order embedding. At the same time, the noise problem also affects the quality of embedded expression. We introduce contrastive learning into graph CF to alleviate the noise problem. Contrastive learning optimizes contrastive loss by reducing the distance between positive samples and increasing the distance between negative samples. We use a contrastive learning method through graph perturbation. Specifically, we randomly lose the edges of the graph twice to make contrastive learning between two graphs. At the same time, we also compare different nodes of each subgraph. This contrastive learning method improves the performance of the recommendation model. Experiments show that our model has significantly improved on multiple open datasets. Compared with the baseline, our model has 14% and 31% performance improvements on yelp2018 and book-crossing datasets, respectively, proving that our changes are effective and interpretable.