Deep learning-based models have been widely used to predict electronic health record (EHR) events by exploiting diagnostic characteristics. Despite significant progress, three limitations remain: 1) effectively modeling dynamic relationships among diseases, 2) fully leveraging diagnosis code ontologies from multiple perspectives, and 3) incorporating unstructured discharge summaries. To address these challenges, we propose a coarse-to-fine disease learning framework with patient notes for EHR event prediction, tailored to capture both dynamic and static disease characteristics. First, we construct a fine-grained dynamic disease graph by removing disease weakly correlated disease pairs based on co-occurrence distributions. Second, disease embeddings are refined by integrating coarse and fine-grained information within the hierarchical structure of ICD-9-CM codes. In addition, discharge summaries are combined with auxiliary patient notes for collaborative disease learning. Finally, gated recurrent units, location-based attention, and soft attention mechanisms are utilized to further enhance embedding representations. Experiments on two real-world EHR datasets, MIMIC-III and MIMIC-IV, demonstrate that our model consistently outperforms nine baseline methods in EHR prediction. The source code can be found at https://github.com/YNU-L/CCDLD.

Extracting evolving communities in social networks has attracted much attention recently due to its usefulness in the area of social media. Most existing models assume that network structures evolve monotonically and fail to leverage the fluctuating variation in the real world. Moreover, it is difficult to extract valuable community knowledge from previous snapshots, leading to a negative transfer to the current snapshot. In this article, we design a novel transferring strategy for dynamic community detection based on dual-population cooperation and competition. The transfer strategy guides the search by leveraging the meaningful community structures among previous snapshots based on the similarity between the current and all previous ones. Furthermore, to avoid the problem of insufficient population diversity caused by previous single-population algorithms, this article utilizes dual-population cooperative competition for multiobjective optimization. An intercooperation method effectively interchanges information according to normalized mutual information of different individuals in dual-population. Each population optimizes according to different objectives with a role-oriented teaching–learning-based optimizer to compensate for defects such as many hyperparameters, declining diversity, and insufficient convergence. Top students integrate the fine-grained strategy to mutate boundary nodes depending on embedding-based node activity; Ordinary students fuse the coarse-grained method to separate loosely connected subcommunities, while the bottom students do normal learning. Experimental results indicate that our approach outperforms state-of-the-art methods with high consistency.

Accurate traffic-flow prediction remains a critical challenge due to complicated spatial dependencies, temporal factors, and unpredictable events. Most existing approaches focus on single- or dual-view learning and thus face limitations in systematically learning complex spatial-temporal features. In this work, we propose a novel multiview spatial-temporal transformer (MVSTT) network that can effectively learn complex spatial-temporal domain correlations and potential patterns from multiple views. First, we examine a temporal view and design a short-range gated convolution component from a short-term subview, and a long-range gated convolution component from a long-term subview. These two components effectively aggregate knowledge of the temporal domain at multiple granularities and mine patterns of node evolution across time steps. Meanwhile, in the spatial view, we design a dual-graph spatial learning module that captures fixed and dynamic spatial dependencies of nodes, as well as the evolution patterns of edges, from the static and dynamic graph subviews, respectively. In addition, we further design a spatial-temporal transformer to mine different levels of spatial-temporal features through multiview knowledge fusion. Extensive experiments on four real-world traffic datasets show that our method consistently outperforms the state-of-the-art baseline. The code of MVSTT is available at https://github.com/JianSoL/MVSTT.

User counterparts, such as user attributes in social networks or user interests, are the keys to more natural Human–Computer Interaction (HCI) . In addition, users’ attributes and social structures help us understand the complex interactions in HCI. Most previous studies have been based on supervised learning to improve the performance of HCI. However, in the real world, owing to signal malfunctions in user devices, large amounts of abnormal information, unlabeled data, and unsupervised approaches (e.g., the clustering method) based on mining user attributes are particularly crucial. This paper focuses on improving the clustering performance of users’ attributes in HCI and proposes a deep graph embedding network with feature and structure similarity (called DGENFS ) to cluster users’ attributes in HCI applications based on feature and structure similarity. The DGENFS model consists of a Feature Graph Autoencoder (FGA) module, a Structure Graph Attention Network (SGAT) module, and a Dual Self-supervision (DSS) module. First, we design an attributed graph clustering method to divide users into clusters by making full use of their attributes. To take full advantage of the information of human feature space, a k-neighbor graph is generated as a feature graph based on the similarity between human features. Then, the FGA and SGAT modules are utilized to extract the representations of human features and topological space, respectively. Next, an attention mechanism is further developed to learn the importance weights of different representations to effectively integrate human features and social structures. Finally, to learn cluster-friendly features, the DSS module unifies and integrates the features learned from the FGA and SGAT modules. DSS explores the high-confidence cluster assignment as a soft label to guide the optimization of the entire network. Extensive experiments are conducted on five real-world data sets on user attribute clustering. The experimental results demonstrate that the proposed DGENFS model achieves the most advanced performance compared with nine competitive baselines.

MOTIVATION: Biological experimental approaches to protein-protein interaction (PPI) site prediction are critical for understanding the mechanisms of biochemical processes but are time-consuming and laborious. With the development of Deep Learning (DL) techniques, the most popular Convolutional Neural Networks (CNN)-based methods have been proposed to address these problems. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in protein sequences. Current methods cannot efficiently explore the nature of Position Specific Scoring Matrix (PSSM), secondary structure and raw protein sequences by processing them all together. For PPI site prediction, how to effectively model the PPI context with attention to prediction remains an open problem. In addition, the long-distance dependencies of PPI features are important, which is very challenging for many CNN-based methods because the innate ability of CNN is difficult to outperform auto-regressive models like Transformers. RESULTS: To effectively mine the properties of PPI features, a novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer (MLP-Mixer) module for local feature extraction and a two-stage multi-branch module for global feature capture. The model merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction. On the one hand, this is the first application of an advanced Transformer (i.e. MLP-Mixer) with a hybrid network for sequence-based PPI prediction. On the other hand, unlike existing methods that treat global features altogether, the proposed two-stage multi-branch hybrid module firstly assigns different attention scores to the input features and then encodes the feature through different branch modules. In the first stage, different improved attention modules are hybridized to extract features from the raw protein sequences, secondary structure and PSSM, respectively. In the second stage, a multi-branch network is designed to aggregate information from both branches in parallel. The two branches encode the features and extract dependencies through several operations such as TextCNN, Bi-LSTM and different activation functions. Experimental results on real-world public datasets show that our model consistently achieves state-of-the-art performance over seven remarkable baselines. AVAILABILITY: The source code of HN-PPISP model is available at https://github.com/ylxu05/HN-PPISP.

The "curse of dimensionality" brings new challenges to the feature selection (FS) problem, especially in bioinformatics filed. In this paper, we propose a hybrid Two-Stage Teaching-Learning-Based Optimization (TS-TLBO) algorithm to improve the performance of bioinformatics data classification. In the selection reduction stage, potentially informative features, as well as noisy features, are selected to effectively reduce the search space. In the following comparative self-learning stage, the teacher and the worst student with self-learning evolve together based on the duality of the FS problems to enhance the exploitation capabilities. In addition, an opposition-based learning strategy is utilized to generate initial solutions to rapidly improve the quality of the solutions. We further develop a self-adaptive mutation mechanism to improve the search performance by dynamically adjusting the mutation rate according to the teacher's convergence ability. Moreover, we integrate a differential evolutionary method with TLBO to boost the exploration ability of our algorithm. We conduct comparative experiments on 31 public data sets with different data dimensions, including 7 bioinformatics datasets, and evaluate our TS-TLBO algorithm compared with 11 related methods. The experimental results show that the TS-TLBO algorithm obtains a good feature subset with better classification performance, and indicates its generality to the FS problems.

Traffic flow prediction has great significance for improving road traffic capacity and traffic safety. However, traffic flow in a certain area is usually affected by some factors such as weather, holidays and neighboring areas. So, traffic situation is complicated and traffic flow prediction is difficult. How to use existing traffic data information to predict future traffic flow is the key to this problem. In this paper, we develop an accurate prediction model based on dilated convolution — ST-MINet (Deep Spatio-Temporal Modified-Inception with Dilated convolution Networks). We fully consider the complexity, nonlinearity and uncertainly of traffic network by summarizing various network models such as ResNet and Inception. So, we use the deep space-time residual network to ensure the convolution accuracy of the information’s position distribution on the basis of existing networks. Then, we add the cavity convolution to the model, which can effectively control the field of view of the convolution kernel. In the experimental part, we compare ten classical algorithms with our ST-MINet, it shows that our model has higher accuracy than others.