Graph Learning Research Articles

Learning Graph ODE for Continuous-Time Sequential Recommendation

Learning Graph ODE for Continuous-Time Sequential Recommendation

A Unified Framework for Neurological Disease Detection and Gait Classification Using Deep Graph Learning

A Unified Framework for Neurological Disease Detection and Gait Classification Using Deep Graph Learning

Integrating Knowledge Graph and Machine Learning Methods for Landslide Susceptibility Assessment

The suddenness of landslide disasters often causes significant loss of life and property. Accurate assessment of landslide disaster susceptibility is of great significance in enhancing the ability of accurate disaster prevention. To address the problems of strong subjectivity in the selection of assessment indicators and low efficiency of the assessment process caused by the insufficient application of a priori knowledge in landslide susceptibility assessment, in this paper, we propose a novel landslide susceptibility assessment framework by combing domain knowledge graph and machine learning algorithms. Firstly, we combine unstructured data, extract priori knowledge based on the Unified Structure Generation for Universal Information Extraction Pre-trained model (UIE) fine-tuned with a small amount of labeled data to construct a landslide susceptibility knowledge graph. We use Paired Relation Vectors (PairRE) to characterize the knowledge graph, then construct a target area characterization factor recommendation model by calculating spatial correlation, attribute similarity, Term Frequency–Inverse Document Frequency (TF-IDF) metrics. We select the optimal model and optimal feature combination among six typical machine learning (ML) models to construct interpretable landslide disaster susceptibility assessment mapping. Experimental validation and analysis are carried out on the three gorges area (TGA), and the results show the effectiveness of the feature factors recommended by the knowledge graph characterization learning, with the overall accuracy of the model after adding associated disaster factors reaching 87.2%. The methodology proposed in this research is a better contribution to the knowledge and data-driven assessment of landslide disaster susceptibility.

Influential simplices mining via simplicial convolutional networks

The identification of influential simplices is crucial for understanding higher-order network dynamics. Yet, despite relatively mature research on influential nodes (0-simplices) mining, characterizing simplices’ influence and identifying influential simplices remain challenging due to notable discrepancies in vital nodes and vital simplices mining. In this paper, we propose a higher-order graph learning model, named influential simplices mining neural networks (ISMnet), to identify vital simplices in simplicial complexes. ISMnet leverages novel higher-order representations: hierarchical bipartite graphs and higher-order hierarchical (HoH) Laplacians, where target simplices are grouped into a hub set and can interact with other simplices. It also employs learnable graph convolution operators in each HoH Laplacian domain to capture interactions among simplices and can identify influential simplices of arbitrary order by changing the hub set. Notably, ISMnet addresses the limitations inherent in traditional graph neural networks that struggle with higher-order tasks, while seamlessly retaining the capability to exploit network topology and node features concurrently. Numerical results on empirical and synthetic datasets demonstrate that ISMnet significantly outperforms existing methods by at least 12% and 4%, respectively, in ranking 2-simplices. In general, this novel framework promises to serve as a potent tool in higher-order network analysis.

Consensus representation-driven structured graph learning for multi-view clustering

Consensus representation-driven structured graph learning for multi-view clustering

A weighted multi-view clustering via sparse graph learning

A weighted multi-view clustering via sparse graph learning

Multi-task network with inter-task consistency learning for face parsing and facial expression recognition at real-time speed

In recent years, face parsing and facial expression recognition have attracted increasing interest. Even though there are relevant results about face parsing and face representation, these approaches seek accuracy at the expense of speed. In this paper, we design a novel multi-task learning network for face parsing and facial expression recognition (MPENet). Specifically, MPENet consists of shared encoders and three downstream branches. In the edge perceiving branch, we use category edge and binary edge to extract face boundary information and improve localization of face boundaries. In the segmentation branch, we use graph learning to fuse edge and semantic information of the image, analyze the relations between different feature regions, and capture more contextual relationships. Finally, we design a consistent learning loss function, forcing different branches to learn the same predictions. We have carried out experiments on face datasets, and found that it shows high precision and fast inference speed. Specifically, MPENet achieves F1 scores of 85.9 on the CelebAMask-HQ dataset and 92.9 on the Lapa dataset, with an inference speed of 92.9 FPS. Moreover, MPENet precisely delineates the semantic boundaries of facial regions and, through consistent multi-task learning, effectively facilitates synergy among various tasks.

HpGraphNEI: A network entity identification model based on heterophilous graph learning

Network entities have important asset mapping, vulnerability, and service delivery applications. In cyberspace, where the network structure is complex and the number of entities is large, effectively obtaining the relevant attributes of entities is a difficult task. Graph neural network-based approaches focus on target IP node messaging from neighboring nodes; however, the graph learning task ignores the heterophilous relationship of network entity identification (NEI) tasks in the graph structure and fails to effectively message from non-neighboring nodes. To address the limitations of the existing task, we propose a NEI model based on heterophilous graph learning (HpGraphNEI); HpGraphNEI converts heterophilous graphs under the NEI task into homophilous graphs and uses the graph learning mechanism to carry out attribute completion task for incomplete entity attributes. First, the acquired dataset is feature-extracted by network measurement, and the clustering algorithm is employed to divide the target nodes into communities. Second, the network topology graph is constructed to embed the node attribute information and neighborhood structure information into the graph in the form of feature vectors. Then, the global attention in the community is calculated according to the attention results, the edges with strong correlation in the network are filtered, the adjacency matrix is reconstructed, and then the updated node information is aggregated to complete the incomplete attribute completion. Fourth, the updated nodes are categorized to output network entity categories and construct network entity portraits based on the attribute completion nodes. We conducted a 2-month data collection in three real regions and successfully identified 6 types of network entities. Compared with the optimal baseline, all the metrics have significantly improved, with NEI accuracy above 93.74% and up to 96.28%, improved 2.27% to 2.69%.

Multi-view clustering via dynamic unified bipartite graph learning

Multi-view clustering algorithms based on graph learning have the ability to extract the potential association between data samples, which has been a concern of many researchers in recent years. However, existing algorithms have two limitations: (1) they directly learn from the raw graph, which includes noise and outliers, and they construct the graph filter statically, biasing the clustering results; (2) during graph construction, they mainly use the information of a single structure and fail to fully extract the multi-granular structural information among the data. To address these issues, this paper proposes a novel multi-view clustering method via dynamic unified bipartite graph learning. Specifically, a learnable graph filter is first refined to dynamically filter the original data feature space, gradually filtering out the undesirable high-frequency noise and achieving a clustering-friendly smooth representation. Second, a unified bipartite graph is constructed by combining the multi-granular structural information of different views to better explore the distinct and common information of each view. In one framework, the dynamic filter and multi-granular structure information are combined to iteratively learn the unified bipartite graph. An efficient iterative algorithm is designed to decompose the objective function into small-scale subproblems for solving. Extensive experiments on benchmark datasets show the superiority of the proposed algorithm over several existing state-of-the-art multi-view clustering algorithms.

Discrete-time graph neural networks for transaction prediction in Web3 social platforms

In Web3 social platforms, i.e. social web applications that rely on blockchain technology to support their functionalities, interactions among users are usually multimodal, from common social interactions such as following, liking, or posting, to specific relations given by crypto-token transfers facilitated by the blockchain. In this dynamic and intertwined networked context, modeled as a financial network, our main goals are (i) to predict whether a pair of users will be involved in a financial transaction, i.e. the transaction prediction task, even using textual information produced by users, and (ii) to verify whether performances may be enhanced by textual content. To address the above issues, we compared current snapshot-based temporal graph learning methods and developed T3GNN, a solution based on state-of-the-art temporal graph neural networks’ design, which integrates fine-tuned sentence embeddings and a simple yet effective graph-augmentation strategy for representing content, and historical negative sampling. We evaluated models in a Web3 context by leveraging a novel high-resolution temporal dataset, collected from one of the most used Web3 social platforms, which spans more than one year of financial interactions as well as published textual content. The experimental evaluation has shown that T3GNN consistently achieved the best performance over time and for most of the snapshots. Furthermore, through an extensive analysis of the performance of our model, we show that, despite the graph structure being crucial for making predictions, textual content contains useful information for forecasting transactions, highlighting an interplay between users’ interests and economic relationships in Web3 platforms. Finally, the evaluation has also highlighted the importance of adopting sampling methods alternative to random negative sampling when dealing with prediction tasks on temporal networks.

Deep transformer-based heterogeneous spatiotemporal graph learning for geographical traffic forecasting

Accurate geographical traffic forecasting plays a critical role in urban transportation planning, traffic management, and geospatial artificial intelligence (GeoAI). Although deep learning models have made significant progress in geographical traffic forecasting, they still face challenges in effectively capturing long-term temporal dependencies and modeling heterogeneous dynamic spatial dependencies. To address these issues, we propose a novel deep transformer-based heterogeneous spatiotemporal graph learning model for geographical traffic forecasting. Our model incorporates a temporal transformer that captures long-term temporal patterns in traffic data without simple data fusion. Furthermore, we introduce adaptive normalized graph structures within different graph layers, enabling the model to capture dynamic spatial dependencies and adapt to diverse traffic scenarios, especially for the heterogeneous relationship. We conduct comprehensive experiments and visualization on four primary public datasets and demonstrate that our model achieves state-of-the-art results in comparison to existing methods.

Sparse dynamic graph learning for district heat load forecasting

Accurate heat load forecasting is crucial for the efficient operation and management of district heating systems. This study introduces a novel Sparse Dynamic Graph Neural Network (SDGNN) framework designed to address the complexities of forecasting heat load in district heating networks. The proposed model represents the district heating network as a dynamic graph, with nodes corresponding to consumers or heat sources and edges denoting temporal dependencies. The SDGNN framework comprises three key components: (1) a sparse graph learning module that identifies the most relevant nodes and edges, (2) a spatio-temporal memory enhancement module that captures both short-term and long-term dependencies, and (3) a temporal fusion module that integrates node representations into a comprehensive global forecast. Evaluated on a real-world district heating dataset from Denmark, the SDGNN model demonstrates superior accuracy and efficiency compared to existing methods. The results indicate that the SDGNN framework effectively captures intricate spatio-temporal patterns in historical heat load data, achieving up to 5.7% improvement in RMSE, 7.4% in MAE, and 5.7% in CVRMSE over baseline models. Additionally, incorporating meteorological factors into the model further enhances its predictive performance. These findings suggest that the SDGNN framework is a robust and scalable solution for district heat load forecasting, with potential applications in other domains involving spatio-temporal graph data.

Parameterized multi-perspective graph learning network for temporal sentence grounding in videos

Parameterized multi-perspective graph learning network for temporal sentence grounding in videos

Concept factorization with adaptive graph learning on Stiefel manifold

Concept factorization with adaptive graph learning on Stiefel manifold

Adaptive multi-scale Graph Neural Architecture Search framework

Graph neural networks (GNNs) have gained significant attention for their ability to learn representations from graph-structured data, in which message passing and feature fusion strategies play an essential role. However, traditional Graph Neural Architecture Search (GNAS) mainly focuses on optimization with a static perceptive field to ease the search process. To efficiently utilize latent relationships between non-adjacent nodes as well as edge features, this work proposes a novel two-stage approach that is able to optimize GNN structures more effectively by adaptively aggregating neighborhood features in multiple scales. This adaptive multi-scale GNAS is able to assign optimal weights for different neighbors in different graphs and learning tasks. In addition, it takes latent relationships and edge features into message passing into account, and can incorporate different feature fusion strategies. Compared with traditional ones, our proposed approach can explore a much larger and more diversified search space efficiently. We also prove that traditional multi-hop GNNs are low-pass filters, which can lead to the removal of important low-frequency components of signals from remote neighbors in a graph, and they are not even expressive enough to distinguish some simple regular graphs, justifying the superiority of our approach. Experiments with seven datasets across three graph learning tasks, including graph regression, node classification, and graph classification, demonstrate that our method yields significant improvement compared with state-of-the-art GNAS approaches and human-designed GNN approaches. Specifically, for example, with our framework, the MAE of the 12-layer AM-GNAS was 0.102 for the ZINC dataset, yielding over 25% improvement.

AutoAMS: Automated attention-based multi-modal graph learning architecture search

Multi-modal attention mechanisms have been successfully used in multi-modal graph learning for various tasks. However, existing attention-based multi-modal graph learning (AMGL) architectures heavily rely on manual design, requiring huge effort and expert experience. Meanwhile, graph neural architecture search (GNAS) has made great progress toward automatically designing graph-based learning architectures. However, it is challenging to directly adopt existing GNAS methods to search for better AMGL architectures because of the search spaces that only focus on designing graph neural network architectures and the search objective that ignores multi-modal interactive information between modalities and long-term content dependencies within different modalities. To address these issues, we propose an automated attention-based multi-modal graph learning architecture search (AutoAMS) framework, which can automatically design the optimal AMGL architectures for different multi-modal tasks. Specifically, we design an effective attention-based multi-modal (AM) search space consisting of four sub-spaces, which can jointly support the automatic search of multi-modal attention representation and other components of multi-modal graph learning architecture. In addition, a novel search objective based on an unsupervised multi-modal reconstruction loss and task-specific loss is introduced to search and train AMGL architectures. The search objective can extract the global features and capture multi-modal interactions from multiple modalities. The experimental results on multi-modal tasks show strong evidence that AutoAMS is capable of designing high-performance AMGL architectures.

PGCNMDA: Learning node representations along paths with graph convolutional network for predicting miRNA-disease associations

Identifying miRNA-disease associations (MDAs) is crucial for improving the diagnosis and treatment of various diseases. However, biological experiments can be time-consuming and expensive. To overcome these challenges, computational approaches have been developed, with Graph Convolutional Network (GCN) showing promising results in MDA prediction. The success of GCN-based methods relies on learning a meaningful spatial operator to extract effective node feature representations. To enhance the inference of MDAs, we propose a novel method called PGCNMDA, which employs graph convolutional networks with a learning graph spatial operator from paths. This approach enables the generation of meaningful spatial convolutions from paths in GCN, leading to improved prediction performance. On HMDD v2.0, PGCNMDA obtains a mean AUC of 0.9229 and an AUPRC of 0.9206 under 5-fold cross-validation (5-CV), and a mean AUC of 0.9235 and an AUPRC of 0.9212 under 10-fold cross-validation (10-CV), respectively. Additionally, the AUC of PGCNMDA also reaches 0.9238 under global leave-one-out cross-validation (GLOOCV). On HMDD v3.2, PGCNMDA obtains a mean AUC of 0.9413 and an AUPRC of 0.9417 under 5-CV, and a mean AUC of 0.9419 and an AUPRC of 0.9425 under 10-CV, respectively. Furthermore, the AUC of PGCNMDA also reaches 0.9415 under GLOOCV. The results show that PGCNMDA is superior to other compared methods. In addition, the case studies on pancreatic neoplasms, thyroid neoplasms and leukemia show that 50, 50 and 48 of the top 50 predicted miRNAs linked to these diseases are confirmed, respectively. It further validates the effectiveness and feasibility of PGCNMDA in practical applications.

KaTaGCN: Knowledge-Augmented and Time-Aware Graph Convolutional Network for efficient traffic forecasting

Dynamic spatio-temporal dependencies and temporal patterns in traffic series are critical factors affecting traffic forecasting accuracy. Due to the intrinsic challenges of incorporating explicit, logical knowledge into the implicit black-box learning process of neural networks, only a few methods effectively use prior knowledge to improve the learning of traffic forecasting. To tackle this problem, we introduce a new approach called Knowledge-augmented and Time-aware Graph Convolutional Network, namely KaTaGCN. At its core, we have created a knowledge-augmented module that boosts the diffusion weights between closely related adjacent nodes in graph learning. This is achieved by implementing a new loss function. Then, to learn the periodic implicit relationship between these timestamps and traffic signals, the weights and biases are chosen adaptively to be trained based on the timestamps of each sample. Finally, a gated spatio-temporal mapping module regresses high-dimensional embedded features from spatial and temporal dimensions. KaTaGCN is structured without any attention mechanisms or recurrent neural networks. Extensive experimental results on six real-world public traffic datasets demonstrate that KaTaGCN achieves an average improvement of 4.29% in forecasting performance compared with suboptimal results.

PL4XGL: A Programming Language Approach to Explainable Graph Learning

PL4XGL: A Programming Language Approach to Explainable Graph Learning

GL-GNN: Graph learning via the network of graphs

Graph neural networks (GNNs) have achieved great success in many scenarios with graph-structured data. However, in many real applications, three issues arise when applying GNNs: graphs are unavailable, nodes have noisy features, graphs are incomplete. Aiming at solving these problems, we propose a novel end-to-end graph-learnable GNN, named GL-GNN. GL-GNN includes multiple sub-modules, each sub-module learns key features and the corresponding key relation graphs of samples when graphs are unavailable. The learned graphs are further fused using an aggregation module over the network of graphs, which is obtained by learning the network of sub-modules. GL-GNN solves the first issue by simultaneously learning multiple relation graphs of samples as well as a relation network of graphs, and solves the second and the third issue by selecting key features as well as key graphs. We compare GL-GNN with 12 baseline methods on seven datasets when graphs are unavailable and 16 out of 17 baseline methods on accuracy and F1 score on seven datasets when graphs are available. The results show that GL-GNN achieves better performances than the baseline methods and is capable of learning key features and key graphs from the datasets.