Adaptive Graph Research Articles

Spatio-temporal attention based collaborative local–global learning for traffic flow prediction

Traffic flow prediction is crucial for intelligent transportation systems (ITS), providing valuable insights for traffic control, route planning, and operation management. Existing work often separately models the spatial and temporal dependencies and primarily relies on predefined graphs to represent spatio-temporal dependencies, neglecting the traffic dynamics caused by unexpected events and the global relationships among road segments. Unlike previous models that primarily focus on local feature extraction, we propose a novel collaborative local–global learning model (LOGO) that employs spatio-temporal attention (STA) and graph convolutional networks (GCN). Specifically, LOGO simultaneously extracts hidden traffic features from both local and global perspectives. In local feature extraction, a novel STA is devised to directly attend to spatio-temporal coupling interdependencies instead of separately modeling temporal and spatial dependencies, and to capture in-depth spatio-temporal traffic context with an adaptive graph focusing on the dynamics in traffic flow. In global feature extraction, a global correlation matrix is constructed and GCNs are utilized to propagate messages on the obtained matrix to achieve interactions between both adjacent and similar road segments. Finally, the obtained local and global features are concatenated and fed into a gated aggregation to forecast future traffic flow. Extensive experiments on four real-world traffic datasets sourced from the Caltrans Performance Measurement System (PEMS03, PEMS04, PEMS07, and PEMS08) demonstrate the effectiveness of our proposed model. LOGO achieves the best performance over 18 state-of-the-art baselines and the best prediction performance with the highest improvement of 6.06% on the PEMS07 dataset. Additionally, two real-world case studies further substantiate the robustness and interpretability of LOGO.

DPFANet: Deep Point Feature Aggregation Network for Classification of Irregular Objects in LIDAR Point Clouds

Point cloud data acquired by scanning with Light Detection and Ranging (LiDAR) devices typically contain irregular objects, such as trees, which lead to low classification accuracy in existing point cloud classification methods. Consequently, this paper proposes a deep point feature aggregation network (DPFANet) that integrates adaptive graph convolution and space-filling curve sampling modules to effectively address the feature extraction problem for irregular object point clouds. To refine the feature representation, we utilize the affinity matrix to quantify inter-channel relationships and adjust the input feature matrix accordingly, thereby improving the classification accuracy of the object point cloud. To validate the effectiveness of the proposed approach, a TreeNet dataset was created, comprising four categories of tree point clouds derived from publicly available UAV point cloud data. The experimental findings illustrate that the model attains a mean accuracy of 91.4% on the ModelNet40 dataset, comparable to prevailing state-of-the-art techniques. When applied to the more challenging TreeNet dataset, the model achieves a mean accuracy of 88.0%, surpassing existing state-of-the-art methods in all classification metrics. These results underscore the high potential of the model for point cloud classification of irregular objects.

AdaGIN: Adaptive Graph Interaction Network for Click-Through Rate Prediction

The goal of click-through rate (CTR) prediction in recommender systems is to effectively work with input features. However, existing CTR prediction models face three main issues. First, many models use a basic approach for feature combinations, leading to noise and reduced accuracy. Second, there is no consideration for the varying importance of features in different interaction orders, affecting model performance. Third, current model architectures struggle to capture different interaction signals from various semantic spaces, leading to sub-optimal performance. To address these issues, we propose the Adaptive Graph Interaction Network (AdaGIN) with the Graph Neural Networks-based Feature Interaction Module (GFIM), the Multi-semantic Feature Interaction Module (MFIM), and the Negative Feedback-based Search (NFS) algorithm. GFIM explicitly aggregates information between features and assesses their importance, while MFIM captures information from different semantic spaces. NFS uses negative feedback to optimize model complexity. Experimental results show AdaGIN outperforms existing models on large-scale public benchmark datasets.

TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting.

Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods.

A robust semi-supervised regressor with correntropy-induced manifold regularization and adaptive graph

A robust semi-supervised regressor with correntropy-induced manifold regularization and adaptive graph

Multistream Adaptive Attention-Enhanced Graph Convolutional Networks for Youth Fencing Footwork Training.

The popularity of fencing and intense sports competition has burdened adolescents with excessive training, harming their immature bodies. Traditional training methods fail to provide timely movement corrections and personalized plans, leading to ineffective exercises. This paper aims to use artificial intelligence technology to reduce ineffective exercises and alleviate the training burden. We propose an action recognition algorithm based on the characteristics of adolescent athletes. This algorithm uses multimodal input data to comprehensively extract action information. Each modality is processed by the same network structure, utilizing attention mechanisms and adaptive graph structures. A multibranch feature fusion method is used to determine the final action category. We gathered the fencing footwork data set 2.0. Our model achieved 93.3% accuracy, with the highest precision at 95.8% and the highest F1-Score at 94.5% across all categories. It effectively recognized actions of adolescents with different heights and speeds, outperforming traditional methods. Our artificial intelligence-based training solution improves training efficiency and reduces the training burden on adolescents.

An OD time prediction model based on adaptive graph embedding

An OD time prediction model based on adaptive graph embedding

TAGL: Temporal-Guided Adaptive Graph Learning Network for Coordinated Movement Classification

TAGL: Temporal-Guided Adaptive Graph Learning Network for Coordinated Movement Classification

Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)

Graph convolutional networks (GCNs) are an effective skeleton-based human action recognition (HAR) technique. GCNs enable the specification of CNNs to a non-Euclidean frame that is more flexible. The previous GCN-based models still have a lot of issues: (I) The graph structure is the same for all model layers and input data. GCN model's hierarchical structure and human action recognition input diversity make this a problematic approach; (II) Bone length and orientation are understudied due to their significance and variance in HAR. For this purpose, we introduce an Extended Multi-stream Temporal-attention Adaptive GCN (EMS-TAGCN). By training the network topology of the proposed model either consistently or independently according to the input data, this data-based technique makes graphs more flexible and faster to adapt to a new dataset. A spatial, temporal, and channel attention module helps the adaptive graph convolutional layer focus on joints, frames, and features. Hence, a multi-stream framework representing bones, joints, and their motion enhances recognition accuracy. Our proposed model outperforms the NTU RGBD for CS and CV by 0.6% and 1.4%, respectively, while Kinetics-skeleton Top-1 and Top-5 are 1.4% improved, UCF-101 has improved 2.34% accuracy and HMDB-51 dataset has significantly improved 1.8% accuracy. According to the results, our model has performed better than the other models. Our model consistently outperformed other models, and the results were statistically significant that demonstrating the superiority of our model for the task of HAR and its ability to provide the most reliable and accurate results.

Batch process soft sensing based on data-stacking multiscale adaptive graph neural network

Abstract Soft sensing technology has found extensive application in predicting key quality variables in batch processes. However, its application in batch process is limited by the uneven batch length, the correlation of data and the difficulty in extracting the dependencies between variables and within variables. To address these issues, we propose a data-stacking multiscale adaptive graph neural network (DSMAGNN) soft sensor model. Firstly, Mutual information (MI) is used to selected quality-related variables, the 3D batch data is converted into a time-delay sequence suitable for input to the soft sensor model through the data stacking strategy, and the underlying time correlation at different time scales is preserved by incorporating the multi-scale pyramid network. Secondly, the dependencies between variables are inferred by the adaptive graph learning module, while the dependencies both within and between variables are modeled by the multi-scale temporal graph neural network. Thirdly, collaborative work across different time scales is further facilitated by the scale fusion module. Finally, the feasibility and effectiveness of the model are verified through experiments in the industrial-scale penicillin fermentation process and hot rolling process. (DSMAGNN) soft sensor model. Firstly, MI is used to selected quality-related variables, and the data stacking strategy is employed to convert 3D batch data into a time-delay sequence suitable for input to the soft sensor model. A multiscale pyramid network is utilized to preserve the underlying time dependence across different time scales. Secondly, since the dependence relationship between variables may vary across different time scales, the adaptive graph learning modules deduce scale-specific variable dependencies without relying on predefined priors. Thirdly, given the multiscale feature representation and the inferred dependency relationships between scale-specific variables, we introduce a multiscale temporal graph neural network to jointly model dependencies within and between variables. Building upon this foundation, the scale fusion module is deployed to facilitate collaboration across different temporal scales and automatically capture the significance of contributing temporal patterns. We validate the feasibility and effectiveness of the proposed model through experiments conducted in industrial-scale penicillin fermentation and hot continuous rolling processes, the results show that the proposed model is superior to several compared models, thus confirming its validity.

Ensemble-Enhanced Semi-Supervised Learning with Optimized Graph Construction for High-Dimensional Data.

Graph-based methods have demonstrated exceptional performance in semi-supervised classification. However, existing graph-based methods typically construct either a predefined graph in the original space or an adaptive graph within the output space, which often limits their ability to fully utilize prior information and capture the optimal intrinsic data distribution, particularly in high-dimensional data with abundant redundant and noisy features. This paper introduces a novel approach: Semi-Supervised Classification with Optimized Graph Construction (SSC-OGC). SSC-OGC leverages both predefined and adaptive graphs to explore intrinsic data distribution and effectively employ prior information. Additionally, a graph constraint regularization term (GCR) and a collaborative constraint regularization term (CCR) are incorporated to further enhance the quality of the adaptive graph structure and the learned subspace, respectively. To eliminate the negative effect of constructing a predefined graph in the original data space, we further propose a Hybrid Subspace Ensemble-enhanced framework based on the proposed Optimized Graph Construction method (HSE-OGC). Specifically, we construct multiple hybrid subspaces, which consist of meticulously chosen features from the original data to achieve high-quality and diverse space representations. Then, HSE-OGC constructs multiple predefined graphs within hybrid subspaces and trains multiple SSC-OGC classifiers to complement each other, significantly improving the overall performance. Experimental results conducted on various high-dimensional datasets demonstrate that HSE-OGC exhibits outstanding performance.

Dynamic Spatial-Temporal Embedding via Neural Conditional Random Field for Multivariate Time Series Forecasting

How to capture dynamic spatial-temporal dependencies remains an open question in multivariate time series (MTS) forecasting. Although recent advanced spatial-temporal graph neural networks (STGNNs) achieve superior forecasting performance, they either consider pre-defined spatial correlations or simply learn static graphs. Some research has tried to learn many adjacent matrices to reveal time-varying spatial correlations, but they generate discrete graphs which cannot encode evolutionary information and also face computational complexity problem. In this article, we propose two significant plugins to help automatically learn enhanced dynamic spatial-temporal embedding of MTS data: (1) a novel neural conditional random field (CRF) layer. We find that the implicit time-varying spatial dependencies are reflected by the explicit changeable links between edges, and we propose the neural CRF to encode such pairwise changeable evolutionary inter-dependencies; (2) a structure adaptive graph convolution (SAGC) that does not require pre-defined graphs to capture semantically richer spatial correlations. Then, we integrate the neural CRF, SAGC with recurrent neural network to develop a new STGNN paradigm termed Adaptive Spatial-Temporal graph neural network with Conditional Random Field (ASTCRF), which can be trained in an end-to-end fashion. We validate the effectiveness, efficiency, and scalability of ASTCRF on five public benchmark MTS datasets.

A Non-Contact AI-Based Approach to Multi-Failure Detection in Avionic Systems

The increasing electrification and integration of advanced controls in modern aircraft designs have significantly raised the number and complexity of installed printed circuit boards (PCBs), posing new challenges for efficient maintenance and rapid failure detection. Despite self-diagnostic features in current avionics systems, circuit damage and multiple simultaneous failures may arise, compromising safety and diagnostic accuracy. To address these challenges, this paper aims to develop a fast, accurate, and non-destructive, multi-failure diagnosis algorithm for PCBs. The proposed method combines a self-attention mechanism with an adaptive graph convolutional neural network to enhance diagnostic precision. A convolutional neural network with residual connections extracts features from scalar magnetic field data, ensuring robust input diversity. The model was tested on a typical dual-phase amplitude boosting circuit with up to four different simultaneous failures, achieving the experimental results of 99.08%, 98.50%, 98.78%, 98.01%, 98.93%, 98.25%, 97.03%, and 99.77% across metrics including overall precision, per-class precision, overall recall, per-class recall, overall F1 measure, and per-class F1 measure. The results demonstrated its effectiveness and feasibility in diagnosing complex PCBs with multiple failures, indicating the algorithm’s potential to improve failure diagnosis performance and offer a promising PCB diagnosis solution in aerospace applications.

Modeling the Causes of Urban Traffic Crashes: Accounting for Spatiotemporal Instability in Cities

Traffic crashes have become one of the key public health issues, triggering significant apprehension among citizens and urban authorities. However, prior studies have often been limited by their inability to fully capture the dynamic and complex nature of spatiotemporal instability in urban traffic crashes, typically focusing on static or purely spatial effects. Addressing this gap, our study employs a novel methodological framework that integrates an Integrated Nested Laplace Approximation (INLA)-based Stochastic Partial Differential Equation (SPDE) model with spatially adaptive graph structures, which enables the effective handling of vast and intricate geospatial data while accounting for spatiotemporal instability. This approach represents a significant advancement over conventional models, which often fail to account for the fluid interplay between time-varying weather conditions, geographical attributes, and crash severity. We applied this methodology to analyze traffic crashes across three major U.S. cities—New York, Los Angeles, and Houston—using comprehensive crash data from 2016 to 2019. Our findings reveal city-specific disparities in the factors influencing severe traffic crashes, which are defined as incidents resulting in at least one person sustaining serious injury or death. Despite some universal trends, such as the risk-enhancing effect of cold weather and pedestrian crossings, we find marked differences across cities in relation to factors like temperature, precipitation, and the presence of certain traffic facilities. Additionally, the adjustment observed in the spatiotemporal standard deviations, with values such as 0.85 for New York and 0.471 for Los Angeles, underscores the varying levels of annual temporal instability across cities, indicating that the fluctuation in crash severity factors over time differs markedly among cities. These results underscore the limitations of traditional modeling approaches, demonstrating the superiority of our spatiotemporal method in capturing the heterogeneity of urban traffic crashes. This work has important policy implications, suggesting a need for tailored, location-specific strategies to improve traffic safety, thereby aiding authorities in better resource allocation and strategic planning.

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

Geometry-Aware Enhanced Mutual-Supervised Point Elimination with Overlapping Mask Contrastive Learning for Partitial Point Cloud Registration

Point cloud registration is one of the fundamental tasks in computer vision, but faces challenges under low overlap conditions. Recent approaches use transformers and overlapping masks to improve perception, but mask learning only considers Euclidean distances between features, ignores mismatches caused by fuzzy geometric structures, and is often computationally inefficient. To address these issues, we introduce a novel matching framework. Firstly, we fuse adaptive graph convolution with PPF features to obtain rich feature perception. Subsequently, we construct a PGT framework that uses GeoTransformer and combines it with location information encoding to enhance the geometry perception between source and target clouds. In addition, we improve the visibility of overlapping regions through information exchange and the AIS module, aiming at subsequent keypoint extraction, preserving points with distinct geometrical structures while suppressing the influence of non-overlapping regions to improve computational efficiency. Finally, the mask is refined through contrast learning to preserve geometric and distance similarity, which helps to compute the transformation parameters more accurately. We have conducted comprehensive experiments on synthetic and real-world scene datasets, demonstrating superior registration performance compared to recent deep learning methods. Our approach shows remarkable improvements of 68.21% in RRMSE and 76.31% in tRMSE on synthetic data, while also excelling in real-world scenarios with enhancements of 76.46% in RRMSE and 45.16% in tRMSE.

Dual-level adaptive incongruity-enhanced model for multimodal sarcasm detection

Multimodal sarcasm detection leverages multimodal information, such as image, text, etc. to identify special instances whose superficial emotional expression is contrary to the actual emotion. Existing methods primarily focused on the incongruity between text and image information for sarcasm detection. Existing sarcasm methods in which the tendency of image encoders to encode similar images into similar vectors, and the introduction of noise in graph-level feature extraction due to negative correlations caused by the accumulation of GAT layers and the lack of representations for non-neighboring nodes. To address these limitations, we propose a Dual-Level Adaptive Incongruity-Enhanced Model (DAIE) to extract the incongruity between the text and image at both token and graph levels. At the token level, we bolster token-level contrastive learning with patch-based reconstructed image to capture common and specific features of images, thereby amplifying incongruities between text and images. At the graph level, we introduce adaptive graph contrast learning, coupled with negative pair similarity weights, to refine the feature representation of the model’s textual and visual graph nodes, while also enhancing the information exchange among neighboring nodes. We conduct experiments using a publicly available sarcasm detection dataset. The results demonstrate the effectiveness of our method, outperforming several state-of-the-art approaches by 3.33% and 4.34% on accuracy and F1 score, respectively.

INCOMPLETE multi-view clustering based on low-rank adaptive graph learning

The challenge of acquiring complete data has led to substantial progress in incomplete multi-view clustering (IMVC) methods. Because graph structures can be excellent representations of data structure relationships, exceptional performance in handling incomplete data is demonstrated by graph-based methods at present. However, these methods still have their limitations. Most incomplete multi-view algorithms primarily focus on local information, neglecting global information. Therefore, these methods cannot dynamically recover the structural relationships in incomplete data by harnessing potential information from multiple perspectives and overall structural information. In response to the aforementioned concerns, we introduced an IMVC based on low-rank adaptive graph learning (IMVC-LAGL). This method initially constructs an affinity matrix based on the inter-view adjacency relationships. It also utilizes tensor low-rank constraints and consensus representation learning to explore higher-order correlations among different views. Subsequently, it adaptively reconstructs the incomplete graph structure to ultimately obtain a complete affinity relationship. It leads to excellent clustering results by integrating relevant information within views, overall structural information and potential information from multiple perspectives. We conducted experiments comparing our algorithm with eight incomplete multi-view algorithms using five different evaluation metrics. The results show that our algorithm achieves the best clustering results across eight datasets with varying missing rates. Particularly in the BBCSport dataset and YaleB dataset, the clustering accuracy of our algorithm is improved by 19.83 % and 16.41 %, respectively, compared with the second-best algorithm, under a 50 % missing rate.

TAWFN: a deep learning framework for protein function prediction.

Proteins play pivotal roles in biological systems, and precise prediction of their functions is indispensable for practical applications. Despite the surge in protein sequence data facilitated by high-throughput techniques, unraveling the exact functionalities of proteins still demands considerable time and resources. Currently, numerous methods rely on protein sequences for prediction, while methods targeting protein structures are scarce, often employing convolutional neural networks (CNN) or graph convolutional networks (GCNs) individually. To address these challenges, our approach starts from protein structures and proposes a method that combines CNN and GCN into a unified framework called the two-model adaptive weight fusion network (TAWFN) for protein function prediction. First, amino acid contact maps and sequences are extracted from the protein structure. Then, the sequence is used to generate one-hot encoded features and deep semantic features. These features, along with the constructed graph, are fed into the adaptive graph convolutional networks (AGCN) module and the multi-layer convolutional neural network (MCNN) module as needed, resulting in preliminary classification outcomes. Finally, the preliminary classification results are inputted into the adaptive weight computation network, where adaptive weights are calculated to fuse the initial predictions from both networks, yielding the final prediction result. To evaluate the effectiveness of our method, experiments were conducted on the PDBset and AFset datasets. For molecular function, biological process, and cellular component tasks, TAWFN achieved area under the precision-recall curve (AUPR) values of 0.718, 0.385, and 0.488 respectively, with corresponding Fmax scores of 0.762, 0.628, and 0.693, and Smin scores of 0.326, 0.483, and 0.454. The experimental results demonstrate that TAWFN exhibits promising performance, outperforming existing methods. The TAWFN source code can be found at: https://github.com/ss0830/TAWFN.

Iterative Removal of G-PCC Attribute Compression Artifacts Based on a Graph Neural Network

As a compression standard, Geometry-based Point Cloud Compression (G-PCC) can effectively reduce data by compressing both geometric and attribute information. Even so, due to coding errors and data loss, point clouds (PCs) still face distortion challenges, such as the encoding of attribute information may lead to spatial detail loss and visible artifacts, which negatively impact visual quality. To address these challenges, this paper proposes an iterative removal method for attribute compression artifacts based on a graph neural network. First, the geometric coordinates of the PCs are used to construct a graph that accurately reflects the spatial structure, with the PC attributes treated as signals on the graph’s vertices. Adaptive graph convolution is then employed to dynamically focus on the areas most affected by compression, while a bi-branch attention block is used to restore high-frequency details. To maintain overall visual quality, a spatial consistency mechanism is applied to the recovered PCs. Additionally, an iterative strategy is introduced to correct systematic distortions, such as additive bias, introduced during compression. The experimental results demonstrate that the proposed method produces finer and more realistic visual details, compared to state-of-the-art techniques for PC attribute compression artifact removal. Furthermore, the proposed method significantly reduces the network runtime, enhancing processing efficiency.