The rise of smart devices has accelerated location-based services, creating vast trajectory data for Point-of-Interest (POI) recommendations. However, user omissions or privacy concerns often result in incomplete traj...
详细信息
Bundle recommendation aims to recommend a bundle of items to users as a whole with user-bundle (U-B) interaction information, and auxiliary user-item (U-I) interaction and bundle-item affiliation information. Recent m...
详细信息
ISBN:
(纸本)9781450394086
Bundle recommendation aims to recommend a bundle of items to users as a whole with user-bundle (U-B) interaction information, and auxiliary user-item (U-I) interaction and bundle-item affiliation information. Recent methods usually use two graph neural networks (GNNs) to model user's bundle preferences separately from the U-B graph (bundle view) and U-I graph (item view). However, by conducting statistical analysis, we find that the auxiliary U-I information is far underexplored due to the following reasons: 1) Loosely combining the predicted results cannot well synthesize the knowledge from both views. 2) The local U-B and U-I collaborative relations might not be consistent, leading to GNN's inaccurate modeling of user's bundle preference from the U-I graph. 3) The U-I interactions are usually modeled equally while the significant ones corresponding to user's bundle preference are less emphasized. Based on these analyses, we propose a Distillation-enhanced graph masked autoencoder (DGMAE) for bundle recommendation. Our framework extracts the knowledge of first- and higher-order U-B relations from the U-B graph and injects it into a well-designed graph masked autoencoder (student model). The student model is built with two key designs to jointly capture significant local and global U-I relations from the U-I graph. In specific, we design a transformer-enhanced GNN encoder for global relation learning, which increases the model's representational power of depicting user's bundle preferences. Meanwhile, an adaptive edge masking strategy and reconstruction target are designed on the significant U-I edges to guide the student model to identify the potential ones suggesting user's bundle preferences. Extensive experiments on benchmark datasets show the significant improvements of DGMAE over the SOTA methods.
Inferring small molecule-miRNA associations (MMAs) is crucial for revealing the intricacies of biological processes and disease mechanisms. Deep learning, renowned for its exceptional speed and accuracy, is extensivel...
详细信息
Inferring small molecule-miRNA associations (MMAs) is crucial for revealing the intricacies of biological processes and disease mechanisms. Deep learning, renowned for its exceptional speed and accuracy, is extensively used for predicting MMAs. However, given their heavy reliance on data, inaccuracies during data collection can make these methods susceptible to noise interference. To address this challenge, we introduce the joint masking and self -supervised (JMSS)-MMA model. This model synergizes graphautoencoders with a probability distribution -based masking strategy, effectively countering the impact of noisy data and enabling precise predictions of unknown MMAs. Operating in a self -supervised manner, it deeply encodes the relationship data of small molecules and miRNA through the graphautoencoder, delving into its latent information. Our masking strategy has successfully reduced data noise, enhancing prediction accuracy. To our knowledge, this is the pioneering integration of a masking strategy with graphautoencoders for MMA prediction. Furthermore, the JMSS-MMA model incorporates a node-degree-based decoder, deepening the understanding of the network's structure. Experiments on two mainstream datasets confirm the model's efficiency and precision, and ablation studies further attest to its robustness. We firmly believe that this model will revolutionize drug development, personalized medicine, and biomedical research.
暂无评论