Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph representation. However, there is an inherent gap between self-supervised tasks and downstream tasks in terms of optimization objective and training data. Conventional pre-training methods may be not effective enough on knowledge transfer since they do not make any adaptation for downstream tasks. To solve such problems, we propose a new transfer learning paradigm on GNNs which could effectively leverage self-supervised tasks as auxiliary tasks to help the target task. Our methods would adaptively select and combine different auxiliary tasks with the target task in the fine-tuning stage. We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task. In addition, we learn the weighting model through meta-learning. Our methods can be applied to various transfer learning approaches, it performs well not only in multi-task learning but also in pre-training and fine-tuning. Comprehensive experiments on multiple downstream tasks demonstrate that the proposed methods can effectively combine auxiliary tasks with the target task and significantly improve the performance compared to state-of-the-art methods. CCS CONCEPTS• Computing methodologies → Learning latent representations; Transfer learning; Neural networks.

Concurrent use of multiple drugs can lead to unexpected adverse drug reactions. The interaction between drugs can be confirmed by routine in vitro and clinical trials. However, it is difficult to test the drug–drug interactions widely and effectively before the drugs enter the market. Therefore, the prediction of drug–drug interactions has become one of the research priorities in the biomedical field. In recent years, researchers have been using deep learning to predict drug–drug interactions by exploiting drug structural features and graph theory, and have achieved a series of achievements. A drug–drug interaction prediction model SmileGNN is proposed in this paper, which can be characterized by aggregating the structural features of drugs constructed by SMILES data and the topological features of drugs in knowledge graphs obtained by graph neural networks. The experimental results show that the model proposed in this paper combines a variety of data sources and has a better prediction performance compared with existing prediction models of drug–drug interactions. Five out of the top ten predicted new drug–drug interactions are verified from the latest database, which proves the credibility of SmileGNN.

The main result of this paper is to give that if {b\in\operatorname{Lip}(\mathbb{R}^{n})}, {h_{j}\in\operatorname{BMO}(\mathbb{R}^{n})}, {j=1,\ldots,k}, {k\in\mathbb{Z}^{+}} and {w\in A_{p}}, {1<p<\infty}, then the multilinear Calderón commutators {T_{\Omega,b,\vec{h}}} with variable kernels are bounded on {L^{p}(w)}. In addition, the authors extend the above result to the Morrey space.

Background: The use of multiple drugs at the same time can lead to unexpected adverse drug reactions. The interaction between drugs can be confirmed by routine in vitro and clinical trials. But it is difficult to test the drug-drug interaction widely and effectively before the drug is put into market. Therefore, the prediction of drug-drug interaction has become an important research in biomedical field.Results: In recent years, researchers have used deep learning to predict drug-drug interaction by using drug structural features and graph theory, and they have achieved a series of achievements. A drug-drug interaction prediction model SmileGNN is proposed in this paper. The structural features of drugs are constructed by using SMILES data. The topological features of drugs in knowledge graph are obtained by graph neural network. The structural and topological features of drugs are aggregated to predict the interaction of new drug pairs. Conclusions: The experimental results show that the model proposed in this paper combines a variety of data sources, and has better prediction performance compared with the existing prediction model of drug-drug interaction prediction. The most striking result is that five out of top ten predicted new interaction of drugs are verified from the latest database, which proves the credibility of SmileGNN.