Message-passing Mechanism Research Articles

Hierarchical Graph Neural Network: A Lightweight Image Matching Model with Enhanced Message Passing of Local and Global Information in Hierarchical Graph Neural Networks

Graph Neural Networks (GNNs) have gained popularity in image matching methods, proving useful for various computer vision tasks like Structure from Motion (SfM) and 3D reconstruction. A well-known example is SuperGlue. Lightweight variants, such as LightGlue, have been developed with a focus on stacking fewer GNN layers compared to SuperGlue. This paper proposes the h-GNN, a lightweight image matching model, with improvements in the two processing modules, the GNN and matching modules. After image features are detected and described as keypoint nodes of a base graph, the GNN module, which primarily aims at increasing the h-GNN’s depth, creates successive hierarchies of compressed-size graphs from the base graph through a clustering technique termed SC+PCA. SC+PCA combines Principal Component Analysis (PCA) with Spectral Clustering (SC) to enrich nodes with local and global information during graph clustering. A dual non-contrastive clustering loss is used to optimize graph clustering. Additionally, four message-passing mechanisms have been proposed to only update node representations within a graph cluster at the same hierarchical level or to update node representations across graph clusters at different hierarchical levels. The matching module performs iterative pairwise matching on the enriched node representations to obtain a scoring matrix. This matrix comprises scores indicating potential correct matches between the image keypoint nodes. The score matrix is refined with a ‘dustbin’ to further suppress unmatched features. There is a reprojection loss used to optimize keypoint match positions. The Sinkhorn algorithm generates a final partial assignment from the refined score matrix. Experimental results demonstrate the performance of the proposed h-GNN against competing state-of-the-art (SOTA) GNN-based methods on several image matching tasks under homography, estimation, indoor and outdoor camera pose estimation, and 3D reconstruction on multiple datasets. Experiments also demonstrate improved computational memory and runtime, approximately 38.1% and 26.14% lower than SuperGlue, and an average of about 6.8% and 7.1% lower than LightGlue. Future research will explore the effects of integrating more recent simplicial message-passing mechanisms, which concurrently update both node and edge representations, into our proposed model.

Structure-inclusive similarity based directed GNN: a method that can control information flow to predict drug-target binding affinity.

Exploring the association between drugs and targets is essential for drug discovery and repurposing. Comparing with the traditional methods that regard the exploration as a binary classification task, predicting the drug-target binding affinity can provide more specific information. Many studies work based on the assumption that similar drugs may interact with the same target. These methods constructed a symmetric graph according to the undirected drug similarity or target similarity. Although these similarities can measure the difference between two molecules, it is unable to analyze the inclusion relationship of their substructure. For example, if drug A contains all the substructures of drug B, then in the message-passing mechanism of the graph neural network, drug A should acquire all the properties of drug B, while drug B should only obtain some of the properties of A. To this end, we proposed a structure-inclusive similarity (SIS) which measures the similarity of two drugs by considering the inclusion relationship of their substructures. Based on SIS, we constructed a drug graph and a target graph, respectively, and predicted the binding affinities between drugs and targets by a graph convolutional network-based model. Experimental results show that considering the inclusion relationship of the substructure of two molecules can effectively improve the accuracy of the prediction model. The performance of our SIS-based prediction method outperforms several state-of-the-art methods for drug-target binding affinity prediction. The case studies demonstrate that our model is a practical tool to predict the binding affinity between drugs and targets. Source codes and data are available at https://github.com/HuangStomach/SISDTA.

PathMLP: Smooth path towards high-order homophily

Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance. Intriguingly, from the observation of heterophilous data, we notice that certain high-order information exhibits higher homophily, which motivates us to involve high-order information in node representation learning. However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: (1) over-smoothing due to excessive model depth and propagation times; (2) high-order information is not fully utilized; (3) low computational efficiency. In this regard, we design a similarity-based path sampling strategy to capture smooth paths containing high-order homophily. Then we propose a lightweight model based on multi-layer perceptrons (MLP), named PathMLP, which can encode messages carried by paths via simple transformation and concatenation operations, and effectively learn node representations in heterophilous graphs through adaptive path aggregation. Extensive experiments demonstrate that our method outperforms baselines on 16 out of 20 datasets, underlining its effectiveness and superiority in alleviating the heterophily problem. In addition, our method is immune to over-smoothing and has high computational efficiency. The source code will be available in https://github.com/Graph4Sec-Team/PathMLP.

GTC: GNN-Transformer co-contrastive learning for self-supervised heterogeneous graph representation

Graph Neural Networks (GNNs) have emerged as the most powerful weapon for various graph tasks due to the message-passing mechanism’s great local information aggregation ability. However, over-smoothing has always hindered GNNs from going deeper and capturing multi-hop neighbors. Meanwhile, most methods follow a semi-supervised learning manner, the label scarcity would limit their applicability in real-world systems. Unlike GNNs, Transformers can model global information and multi-hop interactions via multi-head self-attention and a proper Transformer structure can show more immunity to over-smoothing. So, can we propose a novel framework to combine GNN and Transformer, integrating both GNN’s local information aggregation and Transformer’s global information modeling ability to eliminate the over-smoothing problem and achieve self-supervised graph representation? To realize this, this paper proposes a collaborative learning scheme for GNN-Transformer and constructs GTC architecture. GTC leverages the GNN and Transformer branch to encode node information from different views respectively, and establishes contrastive learning tasks based on the encoded cross-view information to realize self-supervised heterogeneous graph representation. For the Transformer branch, we propose Metapath-aware Hop2Token and CG-Hetphormer, which can cooperate with GNNs to attentively encode neighborhood information from different levels. As far as we know, this is the first attempt in the field of graph representation learning to utilize both GNNs and Transformer to collaboratively capture different view information and conduct cross-view contrastive learning. The experiments on real datasets show that GTC exhibits superior performance compared with state-of-the-art methods. Codes can be available at https://github.com/PHD-lanyu/GTC.

Learning solid dynamics with graph neural network

Deep learning has shown great promise in solid physic dynamic simulation. By incorporating physical laws, recent works have further improved performance. However, existing methods rarely conform to macrophysics and incur computational costs. Furthermore, the velocity direction features of the current model have not been decomposed, forcing the model to learn vector operations. To address the aforementioned problems, we propose a Solid-Graph Network (Solid-GN), designed for more accurate and efficient learning of solid dynamics. Firstly, we design a novel and cost-effective symmetric direction encoding system that achieves macroscopic equivariance in 2D space by representing same relative directional relationships among particle pairs and their flipping version. Secondly, we propose a message-passing mechanism incorporated with the contact process, facilitating an accurate description of interactions through the decomposition of normal and tangential effects. Lastly, four novel datasets for solid dynamics with non-uniform radius particles are released, thereby enabling more complex and realistic physical simulations. Experimental evaluations conducted on five datasets demonstrate our model's performance concerning predictive accuracy, macroscopic equivariance, and computational cost over the state-of-the-art ones.

StructGNN: An efficient graph neural network framework for static structural analysis

In the field of structural analysis prediction via supervised learning, neural networks are widely employed. Recent advances in graph neural networks (GNNs) have expanded their capabilities, enabling the prediction of structures with diverse geometries by utilizing graph representations and GNNs' message-passing mechanism. However, conventional message-passing in GNNs doesn't align with structural properties, resulting in inefficient computation and limited generalization to extrapolated datasets. To address this, a novel structural graph representation, incorporating pseudo nodes as rigid diaphragms in each story, alongside an efficient GNN framework called StructGNN is proposed. StructGNN employs an adaptive message-passing mechanism tailored to the structure's story count, enabling seamless transmission of input loading features across the structural graph. Extensive experiments validate the effectiveness of this approach, achieving over 99% accuracy in predicting displacements, bending moments, and shear forces. StructGNN also exhibits strong generalization over non-GNN models, with an average accuracy of 96% on taller, unseen structures. These results highlight StructGNN's potential as a reliable, computationally efficient tool for static structural response prediction, offering promise for addressing challenges associated with dynamic seismic loads in structural analysis.

OGNNMDA: a computational model for microbe-drug association prediction based on ordered message-passing graph neural networks.

In recent years, many excellent computational models have emerged in microbe-drug association prediction, but their performance still has room for improvement. This paper proposed the OGNNMDA framework, which applied an ordered message-passing mechanism to distinguish the different neighbor information in each message propagation layer, and it achieved a better embedding ability through deeper network layers. Firstly, the method calculates four similarity matrices based on microbe functional similarity, drug chemical structure similarity, and their respective Gaussian interaction profile kernel similarity. After integrating these similarity matrices, it concatenates the integrated similarity matrix with the known association matrix to obtain the microbe-drug heterogeneous matrix. Secondly, it uses a multi-layer ordered message-passing graph neural network encoder to encode the heterogeneous network and the known association information adjacency matrix, thereby obtaining the final embedding features of the microbe-drugs. Finally, it inputs the embedding features into the bilinear decoder to get the final prediction results. The OGNNMDA method performed comparative experiments, ablation experiments, and case studies on the aBiofilm, MDAD and DrugVirus datasets using 5-fold cross-validation. The experimental results showed that OGNNMDA showed the strongest prediction performance on aBiofilm and MDAD and obtained sub-optimal results on DrugVirus. In addition, the case studies on well-known drugs and microbes also support the effectiveness of the OGNNMDA method. Source codes and data are available at: https://github.com/yyzg/OGNNMDA.

Graph neural architecture search with heterogeneous message-passing mechanisms

Graph neural architecture search with heterogeneous message-passing mechanisms

MaskArmor: Confidence masking-based defense mechanism for GNN against MIA

Graph neural networks (GNNs) have demonstrated remarkable performance in diverse graph-related tasks, including node classification, graph classification, link prediction, etc. Previous research has indicated that GNNs are vulnerable to membership inference attacks (MIA). These attacks enable malevolent parties to deduce whether the data points are part of the training set by identifying the output distribution, giving rise to noteworthy privacy apprehensions, especially when the graph contains sensitive data. There have been some studies to defend against graph MIA so far, but they have issues like high computational cost and decreased model accuracy. In this paper, we introduce a novel defense framework called MaskArmor, designed to bolster the privacy and security of GNNs against MIA. The MaskArmor framework encompasses four distinct masking strategies: AdjMask, DTMask, ATMask, and SigMask. These strategies leverage message-passing mechanisms, distillation temperature, hybrid masking, and the Sigmoid function, respectively. The MaskArmor framework effectively obscures the distribution of the model on both the training and non-training samples, rendering it challenging for attackers to ascertain whether particular samples have undergone training. Additionally, MaskArmor sustains the model's precision with negligible computational overhead. Our experiments are implemented across seven benchmark datasets and four GNN networks against shadow-based and threshold-based MIAs, showcasing that MaskArmor substantially heightens GNNs' resilience against MIA while simultaneously preserving accuracy on the initial tasks. It also demonstrates adeptness in countering threshold-based MIA through strategies like AdjMask and ATMask. Exhaustive experimental results substantiate that MaskArmor outperforms alternative existing approaches, maintaining effectiveness and applicability across diverse datasets and attack scenarios.

A Plug-and-Play Quaternion Message-Passing Module for Molecular Conformation Representation

Graph neural networks have been widely used to represent 3D molecules, which capture molecular attributes and geometric information through various message-passing mechanisms. This study proposes a novel quaternion message-passing (QMP) module that can be plugged into many existing 3D molecular representation models and enhance their power for distinguishing molecular conformations. In particular, our QMP module represents the 3D rotations between one chemical bond and its neighbor bonds as a quaternion sequence. Then, it aggregates the rotations by the chained Hamilton product of the quaternions. The real part of the output quaternion is invariant to the global 3D rotations of molecules but sensitive to the local torsions caused by twisting bonds, providing discriminative information for training molecular conformation representation models. In theory, we prove that considering these features enables invariant GNNs to distinguish the conformations caused by bond torsions. We encapsulate the QMP module with acceleration, so combining existing models with the QMP requires merely one-line code and little computational cost. Experiments on various molecular datasets show that plugging our QMP module into existing invariant GNNs leads to consistent and significant improvements in molecular conformation representation and downstream tasks.

A New Mechanism for Eliminating Implicit Conflict in Graph Contrastive Learning

Graph contrastive learning (GCL) has attracted considerable attention because it can self-supervisedly extract low-dimensional representation of graph data. InfoNCE-based loss function is widely used in graph contrastive learning, which pulls the representations of positive pairs close to each other and pulls the representations of negative pairs away from each other. Recent works mainly focus on designing new augmentation methods or sampling strategies. However, we argue that the widely used InfoNCE-based methods may contain an implicit conflict which seriously confuses models when learning from negative pairs. This conflict is engendered by the encoder's message-passing mechanism and the InfoNCE loss function. As a result, the learned representations between negative samples cannot be far away from each other, compromising the model performance. To our best knowledge, this is the first time to report and analysis this conflict of GCL. To address this problem, we propose a simple but effective method called Partial ignored Graph Contrastive Learning (PiGCL). Specifically, PiGCL first dynamically captures the conflicts during training by detecting the gradient of representation similarities. It then enables the loss function to ignore the conflict, allowing the encoder to adaptively learn the ignored information without self-supervised samples. Extensive experiments demonstrate the effectiveness of our method.

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

GraIL and its variants have shown their promising capacities for inductive relation reasoning on knowledge graphs. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based framework, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments prove the promising capacity of the proposed MINES from various aspects, especially for the superiority, effectiveness, and transfer ability.

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

Time series forecasts of different temporal granularity are widely used in real-world applications, e.g., sales prediction in days and weeks for making different inventory plans. However, these tasks are usually solved separately without ensuring coherence, which is crucial for aligning downstream decisions. Previous works mainly focus on ensuring coherence with some straightforward methods, e.g., aggregation from the forecasts of fine granularity to the coarse ones, and allocation from the coarse granularity to the fine ones. These methods merely take the temporal hierarchical structure to maintain coherence without improving the forecasting accuracy. In this paper, we propose a novel granularity message-passing mechanism (GMP) that leverages temporal hierarchy information to improve forecasting performance and also utilizes an adaptive reconciliation (AR) strategy to maintain coherence without performance loss. Furthermore, we introduce an optimization module to achieve task-based targets while adhering to more real-world constraints. Experiments on real-world datasets demonstrate that our framework (GMP-AR) achieves superior performances on temporal hierarchical forecasting tasks compared to state-of-the-art methods. In addition, our framework has been successfully applied to a real-world task of payment traffic management in Alipay by integrating with the task-based optimization module.

Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction

BackgroundLong noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribute to a better understanding of the pathogenic mechanisms of disease and provide strong support for the development of advanced treatment methods.ResultsTherefore, we present an innovative Node-Adaptive Graph Transformer model for predicting unknown LncRNA-Disease Associations, named NAGTLDA. First, we utilize the node-adaptive feature smoothing (NAFS) method to learn the local feature information of nodes and encode the structural information of the fusion similarity network of diseases and lncRNAs using Structural Deep Network Embedding (SDNE). Next, the Transformer module is used to capture potential association information between the network nodes. Finally, we employ a Transformer module with two multi-headed attention layers for learning global-level embedding fusion. Network structure coding is added as the structural inductive bias of the network to compensate for the missing message-passing mechanism in Transformer. NAGTLDA achieved an average AUC of 0.9531 and AUPR of 0.9537 significantly higher than state-of-the-art methods in 5-fold cross validation. We perform case studies on 4 diseases; 55 out of 60 associations between lncRNAs and diseases have been validated in the literatures. The results demonstrate the enormous potential of the graph Transformer structure to incorporate graph structural information for uncovering lncRNA-disease unknown correlations.ConclusionsOur proposed NAGTLDA model can serve as a highly efficient computational method for predicting biological information associations.

A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

Deep learning has seen significant growth recently and is now applied to a wide range of conventional use cases, including graphs. Graph data provides relational information between elements and is a standard data format for various machine learning and deep learning tasks. Models that can learn from such inputs are essential for working with graph data effectively. This paper identifies nodes and edges within specific applications, such as text, entities, and relations, to create graph structures. Different applications may require various graph neural network (GNN) models. GNNs facilitate the exchange of information between nodes in a graph, enabling them to understand dependencies within the nodes and edges. The paper delves into specific GNN models like graph convolution networks (GCNs), GraphSAGE, and graph attention networks (GATs), which are widely used in various applications today. It also discusses the message-passing mechanism employed by GNN models and examines the strengths and limitations of these models in different domains. Furthermore, the paper explores the diverse applications of GNNs, the datasets commonly used with them, and the Python libraries that support GNN models. It offers an extensive overview of the landscape of GNN research and its practical implementations.

Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure.

Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects.

Ricci Curvature-Based Graph Sparsification for Continual Graph Representation Learning.

Memory replay, which stores a subset of historical data from previous tasks to replay while learning new tasks, exhibits state-of-the-art performance for various continual learning applications on the Euclidean data. While topological information plays a critical role in characterizing graph data, existing memory replay-based graph learning techniques only store individual nodes for replay and do not consider their associated edge information. To this end, based on the message-passing mechanism in graph neural networks (GNNs), we present the Ricci curvature-based graph sparsification technique to perform continual graph representation learning. Specifically, we first develop the subgraph episodic memory (SEM) to store the topological information in the form of computation subgraphs. Next, we sparsify the subgraphs such that they only contain the most informative structures (nodes and edges). The informativeness is evaluated with the Ricci curvature, a theoretically justified metric to estimate the contribution of neighbors to represent a target node. In this way, we can reduce the memory consumption of a computation subgraph from O(dL) to O(1) and enable GNNs to fully utilize the most informative topological information for memory replay. Besides, to ensure the applicability on large graphs, we also provide the theoretically justified surrogate for the Ricci curvature in the sparsification process, which can greatly facilitate the computation. Finally, our empirical studies show that SEM outperforms state-of-the-art approaches significantly on four different public datasets. Unlike existing methods, which mainly focus on task incremental learning (task-IL) setting, SEM also succeeds in the challenging class incremental learning (class-IL) setting in which the model is required to distinguish all learned classes without task indicators and even achieves comparable performance to joint training, which is the performance upper bound for continual learning.

Graph Convolutional Neural Networks With Diverse Negative Samples via Decomposed Determinant Point Processes.

Graph convolutional neural networks (GCNs) have achieved great success in graph representation learning by extracting high-level features from nodes and their topology. Since GCNs generally follow a message-passing mechanism, each node aggregates information from its first-order neighbor to update its representation. As a result, the representations of nodes with edges between them should be positively correlated and thus can be considered positive samples. However, there are more non-neighbor nodes in the whole graph, which provide diverse and useful information for the representation update. Two non-adjacent nodes usually have different representations, which can be seen as negative samples. Besides the node representations, the structural information of the graph is also crucial for learning. In this article, we used quality-diversity decomposition in determinant point processes (DPPs) to obtain diverse negative samples. When defining a distribution on diverse subsets of all non-neighboring nodes, we incorporate both graph structure information and node representations. Since the DPP sampling process requires matrix eigenvalue decomposition, we propose a new shortest-path-base method to improve computational efficiency. Finally, we incorporate the obtained negative samples into the graph convolution operation. The ideas are evaluated empirically in experiments on node classification tasks. These experiments show that the newly proposed methods not only improve the overall performance of standard representation learning but also significantly alleviate over-smoothing problems.

Two-stage GNN-based fraud detection with camouflage identification and enhanced semantics aggregation

Graph neural network (GNN) has got lots of attention recently in the fraud detection task due to its message-passing mechanism, which can aggregate neighbors feature in the information network. While promising, currently most GNN-based fraud detectors fail to identify camouflage caused by fraud with graph structure information and embed entity in deep layer with rich semantics effectively. To solve these problems, we propose a two-stage GNN-based approach with camouflage identification and enhanced semantics aggregation (CIES-GNN) for fraud detection. In the proposed approach, camouflage is identified by reconstructing subgraphs with both node feature and structure information. Detailedly, hidden edges between fraudsters are found by reconstructing a dense subgraph of fraudster nodes, and redundant connections between benign nodes and fraudster nodes are eliminated by reconstructing subgraphs in a label-balance distribution. Moreover, to embed entity in deep layer without semantics obfuscation, the node information is embedded in an enhanced semantics aggregation module, which fuses higher-order information in intra-relation and aggregates semantics in inter-relation respectively. Experiments on two real-world datasets demonstrate that the proposed CIES-GNN outperforms state-of-the-art baselines.

ROS2 Real-time Performance Optimization and Evaluation

Real-time interaction with uncertain and dynamic environments is essential for robotic systems to achieve functions such as visual perception, force interaction, spatial obstacle avoidance, and motion planning. To ensure the reliability and determinism of system execution, a flexible real-time control system architecture and interaction algorithm are required. The ROS framework was designed to improve the reusability of robotic software development by providing a distributed structure, hardware abstraction, message-passing mechanism, and application prototypes. Rich ecosystems for robotic development have been built around ROS1 and ROS2 architectures based on the Linux system. However, because of the fairness scheduling principle of the default Linux system design and the complexity of the kernel, the system does not have real-time computing. To achieve a balance between real-time and non-real-time computing, this paper uses the transmission mechanism of ROS2, combines it with the scheduling mechanism of the Linux operating system, and uses Preempt_RT to enhance the real-time computing of ROS1 and ROS2. The real-time performance evaluation of ROS1 and ROS2 is conducted from multiple perspectives, including throughput, transmission mode, QoS service quality, frequency, number of subscription nodes and EtherCAT master. This paper makes two significant contributions: firstly, it employs Preempt_RT to optimize the native ROS2 system, effectively enhancing the real-time performance of native ROS2 message transmission; secondly, it conducts a comprehensive evaluation of the real-time performance of both native and optimized ROS2 systems. This comparison elucidates the benefits of the optimized ROS2 architecture regarding real-time performance, with results vividly demonstrated through illustrative figures.