Traffic forecasting is pivotal but challenging due to intricate spatio-temporal dynamics. Existing models often apply a uniform spatial mechanism across distinct temporal scales and rely on static feature embeddings. Consequently, they are inadequate in capturing scale-specific spatial heterogeneity and dynamic feature interdependencies. To address these limitations, we propose the Multi-Scale Spatio-Temporal Attention Network (MSSTAN) with a novel dual-branch architecture: (1) A Global-Local Feature Attention Network (GLFAN) that explicitly decouples spatial interactions across decomposed temporal components to capture multi-scale spatial patterns; and (2) A Spatio-Temporal Feature Attention Network (STFAN) that dynamically recalibrates feature importance based on specific spatio-temporal contexts. A dynamic branch fusion mechanism integrates these branches to optimally aggregate their complementary views. Extensive experiments on five real-world datasets demonstrate that MSSTAN achieves state-of-the-art or highly competitive performance, validating its efficacy for traffic forecasting.

Temporal data analysis plays a pivotal role in applications such as weather forecasting, traffic flow management, energy consumption monitoring, and other areas of urban computing. In recent years, temporal data modeling has transitioned from traditional deep learning methods to pre-trained models. However, existing approaches often exhibit significant task-specific limitations, requiring bespoke model designs and extensive domain data for training. To address these challenges, this study introduces KPT, a novel foundation model for temporal data analysis in urban computing. By leveraging temporal competitive attention and feature interaction attention mechanisms, KPT can effectively capture global context, integrate cross-variable features precisely, and achieve universal feature learning across diverse time series tasks. Additionally, the knowledge prompt network facilitates the deep fusion of cross-layer features via an intricate interaction mechanism, enabling the model to identify and align shared temporal patterns across different time series data. These patterns then transformed into knowledge prompts, thereby enhancing the universal feature learning capabilities of the pre-trained model. Experimental results demonstrate that KPT excels in four core temporal analysis tasks within urban computing, outperforming task-specific models. This highlights KPT’s ability to generalize across tasks and underscores its potential as a foundation model for multi-task scenarios in urban computing.

As the spatio-temporal data of a city is not always available, insufficient data would lead to poor performance in some urban prediction tasks. Existing works utilize transfer learning to solve the data scarcity problem, but they ignore the differences in data distributions across cities, which leads to the ineffectiveness of knowledge transfer. In this paper, we propose a domain adversarial model with knowledge transfer for spatio-temporal prediction across cities, entitledCityTrans. Specifically, 1) the self-adaptive spatio-temporal knowledge (namely ST-Knowledge) is mined, to learn the latent spatial and temporal patterns among cities; 2) the domain-adversarial training strategy is introduced to enhance domain invariance; 3) a knowledge attention mechanism is proposed to extract the transferable information from the ST-Knowledge. Note that our CityTrans is an end-to-end domain adversarial spatio-temporal network without two-stage training (i.e., pre-training and fine-tuning). Finally, we conduct extensive experiments on two spatio-temporal prediction tasks: traffic (flow and speed) prediction, and air quality prediction. Experimental results demonstrate that CityTrans outperforms state-of-the-art models on all tasks by a significant margin.

Protein sequences accumulate in large quantities, and the traditional method of annotating protein function by experiment has been unable to bridge the gap between annotated proteins and unannotated proteins. Machine learning-based protein function prediction is an effective approach to solve this problem. Most of the existing methods only use the protein sequence but ignore the three-dimensional structure which is closely related to the protein function. And the hierarchy of protein functions is not adequately considered. To solve this problem, we propose a graph neural network (GNNGO3D) that combines the three-dimensional structure and functional hierarchy learning. GNNGO3D simultaneously uses three kinds of information: protein sequence, tertiary structure, and hierarchical relationship of protein function to predict protein function. The novelty of GNNGO3D lies in that it integrates the learning of functional level information into the method of predicting protein function by using tertiary structure information, fully learning the relationship between protein functions, and helping to better predict protein function. Experimental results show that our method is superior to existing methods for predicting protein function based on sequence and structure.

Cracks are one of the most common and significant types of road surface damage, posing a threat to the safety of pedestrians and vehicles. If left untreated, cracks can lead to severe consequences such as road and bridge collapse. Therefore, it is essential to develop an efficient road crack detection method. Traditional crack identification methods have the problem of being largely affected by the environment and having low recognition accuracy. In this paper, we propose a road crack detection model based on an improved You Only Look Once version 5 (YOLOv5) model that addresses the limitations of existing state-of-the-art crack detection methods in terms of accuracy and detection speed. First, we replace the intersection over union (IoU) loss function with the SCYLLA-IoU (SIoU) loss function for better accuracy. Second, to enhance detection performance, we replace the feature pyramid network (FPN) with a bi-directional feature pyramid network (BiFPN). Finally, to better extract spatial feature information of different sizes, we modify the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 by using Spatial Pyramid Pooling Cross-Stage Partial Connections (SPPCSPC). We evaluated our YOLOv5s-BiFPN-SPPCSPC-SIoU (YOLOv5s-BSS) method on the dataset from the IEEE 2020 Global Road Damage Detection Challenge (GRDDC) and achieved promising results on road damage datasets from China, Japan, and the United States. The [email protected] of different cracks in three datasets reached 84.9%, 54.6%, and 71%. Our method outperforms related methods, with an increase of 0.7%, 0.7%, and 2.8% over YOLOv5s.

Retrosynthesis and forward synthesis prediction are fundamental challenges in organic synthesis, computer-aided synthesis planning (CASP), and computer-aided drug design (CADD). The objective is to predict plausible reactants for a given target product and its corresponding inverse task. With the rapid development of deep learning, numerous approaches have been proposed to solve this problem from various perspectives. The methods based on molecular graphs benefit from their rich features embedded inside but face difficulties in applying existing sequence-based data augmentations due to the permutation invariance of graph structures. In this work, we propose SeqAGraph, a template-free approach that annotates input graphs with its root atom index to ensure compatibility with sequence-based data augmentation. The matrix product for global attention in graph encoders is implemented by indexing, elementwise product, and aggregation to fuse global attention with local message passing without graph padding. Experiments demonstrate that SeqAGraph fully benefits from molecular graphs and sequence-based data augmentation and achieves state-of-the-art accuracy in template-free approaches.

Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this article, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (1D-CNNs) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and spatial correlation features, and the latter is to learn spatial-temporal dependencies. Then we design a jointly hybrid deep learning framework based on one-dimensional CNNs and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. We conduct extensive experimental evaluations using two real-world datasets, and the results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.

Multi-view graph-based clustering aims to provide clustering solutions to multi-view data. However, most existing methods do not give sufficient consideration to weights of different views and require an additional clustering step to produce the final clusters. They also usually optimize their objectives based on fixed graph similarity matrices of all views. In this paper, we propose a general Graph-based Multi-view Clustering (GMC) to tackle these problems. GMC takes the data graph matrices of all views and fuses them to generate a unified graph matrix. The unified graph matrix in turn improves the data graph matrix of each view, and also gives the final clusters directly. The key novelty of GMC is its learning method, which can help the learning of each view graph matrix and the learning of the unified graph matrix in a mutual reinforcement manner. A novel multi-view fusion technique can automatically weight each data graph matrix to derive the unified graph matrix. A rank constraint without introducing a tuning parameter is also imposed on the graph Laplacian matrix of the unified matrix, which helps partition the data points naturally into the required number of clusters. An alternating iterative optimization algorithm is presented to optimize the objective function. Experimental results using both toy data and real-world data demonstrate that the proposed method outperforms state-of-the-art baselines markedly.

Real-world datasets often have representations in multiple views or come from multiple sources. Exploiting consistent or complementary information from multi-view data, multi-view clustering aims to get better clustering quality rather than relying on the individual view. In this paper, we propose a novel multi-view clustering method called multi-view concept clustering based on concept factorization with local manifold regularization, which drives a common consensus representation for multiple views. The local manifold regularization is incorporated into concept factorization to preserve the locally geometrical structure of the data space. Moreover, the weight of each view is learnt automatically and a co-normalized approach is designed to make fusion meaningful in terms of driving the common consensus representation. An iterative optimization algorithm based on the multiplicative rules is developed to minimize the objective function. Experimental results on nine reality datasets involving different fields demonstrate that the proposed method performs better than several state-of-the-art multi-view clustering methods.