Dual Graph Research Articles

Chemical reaction enhanced graph learning for molecule representation.

Molecular representation learning (MRL) models molecules with low-dimensional vectors to support biological and chemical applications. Current methods primarily rely on intrinsic molecular information to learn molecular representations, but they often overlook effectively integrating domain knowledge into MRL. In this article, we develop a reaction-enhanced graph learning (RXGL) framework for MRL, utilizing chemical reactions as domain knowledge. RXGL introduces dual graph learning modules to model molecule representation. One module employs graph convolutions on molecular graphs to capture molecule structures. The other module constructs a reaction-aware graph from chemical reactions and designs a novel graph attention network on this graph to integrate reaction-level relations into molecular modeling. To refine molecule representations, we design a reaction-based relation learning task, which considers the relations between the reactant and product sides in reactions. In addition, we introduce a cross-view contrastive task to strengthen the cooperative associations between molecular and reaction-aware graph learning. Experiment results show that our RXGL achieves strong performance in various downstream tasks, including product prediction, reaction classification, and molecular property prediction. The code is publicly available at https://github.com/coder-ACAC/RLM.

A dual graph neural networks model using sequence embedding as graph nodes for vulnerability detection

Context:Detecting critical to ensure software system security. The traditional static vulnerability detection methods are limited by staff expertise and perform poorly with today’s increasingly complex software systems. Researchers have successfully applied the techniques used in NLP to vulnerability detection as deep learning has developed. The existing deep learning-based vulnerability detection models can be divided into sequence-based and graph-based categories. Sequence-based embedding models cannot use structured information embedded in the code, and graph-based embedding models lack effective node representations. Objective:To solve these problems, we propose a deep learning-based method, DGVD (Double Graph Neural Network for Vulnerability Detection). Methods:We use the sequential neural network approach to extract local semantic features of the code as nodes embedded in the control flow graph. First, we propose a dual graph neural network module (DualGNN) that consists of GCN and GAT. The altered module utilizes two different graph neural networks to obtain the global structural information of the control flow and the relationship between the nodes and fuses the two. Second, we propose a convolution-based feature enhancement module (TC-FE) that uses different convolution kernels of different sizes to capture information at different scales so that subsequent readout layers can better aggregate node information. Results:Experiments demonstrate that DGVD outperforms existing models, obtaining 64.23% vulnerability detection accuracy on CodeXGLUE’s real benchmark dataset. Conclusion:The proposed DGVD achieves better performance than the state-of-the-art DGVD has a more effective source code feature extraction capability on real-world datasets.

Spectral Properties of Dual Unit Gain Graphs

In this paper, we study dual quaternion, dual complex unit gain graphs, and their spectral properties in a unified frame of dual unit gain graphs. Unit dual quaternions represent rigid movements in the 3D space, and have wide applications in robotics and computer graphics. Dual complex numbers have found application in brain science recently. We establish the interlacing theorem for dual unit gain graphs, and show that the spectral radius of a dual unit gain graph is always not greater than the spectral radius of the underlying graph, and these two radii are equal if, and only if, the dual gain graph is balanced. By using dual cosine functions, we establish the closed form of the eigenvalues of adjacency and Laplacian matrices of dual complex and quaternion unit gain cycles. We then show the coefficient theorem holds for dual unit gain graphs. Similar results hold for the spectral radius of the Laplacian matrix of the dual unit gain graph too.

PCP-GC-LM: single-sequence-based protein contact prediction using dual graph convolutional neural network and convolutional neural network

BackgroundRecently, the process of evolution information and the deep learning network has promoted the improvement of protein contact prediction methods. Nevertheless, still remain some bottleneck: (1) One of the bottlenecks is the prediction of orphans and other fewer evolution information proteins. (2) The other bottleneck is the method of predicting single-sequence-based proteins mainly focuses on selecting protein sequence features and tuning the neural network architecture, However, while the deeper neural networks improve prediction accuracy, there is still the problem of increasing the computational burden. Compared with other neural networks in the field of protein prediction, the graph neural network has the following advantages: due to the advantage of revealing the topology structure via graph neural network and being able to take advantage of the hierarchical structure and local connectivity of graph neural networks has certain advantages in capturing the features of different levels of abstraction in protein molecules. When using protein sequence and structure information for joint training, the dependencies between the two kinds of information can be better captured. And it can process protein molecular structures of different lengths and shapes, while traditional neural networks need to convert proteins into fixed-size vectors or matrices for processing.ResultsHere, we propose a single-sequence-based protein contact map predictor PCP-GC-LM, with dual-level graph neural networks and convolution networks. Our method performs better with other single-sequence-based predictors in different independent tests. In addition, to verify the validity of our method against complex protein structures, we will also compare it with other methods in two homodimers protein test sets (DeepHomo test dataset and CASP-CAPRI target dataset). Furthermore, we also perform ablation experiments to demonstrate the necessity of a dual graph network. In all, our framework presents new modules to accurately predict inter-chain contact maps in protein and it’s also useful to analyze interactions in other types of protein complexes.

Urban streets profiling with coupled spatio-temporal characteristics and topological information from the biking perspective

Urban street profiling is the spatio-temporal pattern discovery of street-level urban areas, which plays a vital role in understanding urban structures and dynamics. Due to the natural topology and various geographic characteristics on the streets, it is necessary to combine multi-dimensional spatio-temporal information to understand different profiles of streets. This research aims to develop a street profiling framework according to the coupled characteristics of streets. At the start, a bidirected dual graph and a spatial weighted graph embedding method were used to solve the street representation. Then, the street profiles can be extracted by clustering embedding vectors of streets and feature importance analysis. As the case study, we employed the bike trajectories and street view images in Xiamen, China to depict the geographic attributes of streets. The results can reveal nine spatio-temporal street profiles from the biking perspective, including three spatial distribution patterns and two spatial semantic patterns. Urban streets in the study area show a significant hierarchical pattern because of locations and the spatial lags of the biking behaviors. Meanwhile, the spatio-temporal characteristics of biking behaviors are the main factors of street profiles, though the street environment attributes participate in over half the number of profile types. We further evaluated the profiling ability of the proposed framework and the importance of urban street profiles using coupled characteristics. Overall, this study explored the profiling method for coupling static and dynamic characteristics of urban streets. The profiling results also help understand street usage and experiences by bikers, which have a practical value on the human-oriented classification of streets and further urban development from a geographic view.

Anomaly detection for multivariate time series in IoT using discrete wavelet decomposition and dual graph attention networks

Effective anomaly detection in multivariate time series data is critical to ensuring the security of Internet of Things (IoT) devices and systems. However, building a high precision and low false positive rate anomaly detection model for the complex and volatile IoT environment is a challenging task. This is often due to issues such as a lack of anomaly labeling, high data volatility, and the complexity of device mechanisms. Traditional machine learning algorithms and sequence models frequently fail to account for feature correlation and temporal dependency in anomaly detection. Although deep learning-based anomaly detection methods have progressed, there is still room for improvement in precision, recall, and generalization ability. In this paper, we propose an anomaly detection model called Meta-MWDG to address these issues. The model is based on a multi-scale discrete wavelet decomposition and a dual graph attention network, which can effectively extract feature correlation and temporal dependency in multivariate time series data. Additionally, model-agnostic meta-learning (MAML) is introduced to improve the model’s generalization performance, enabling it to perform well on new tasks even with a few samples. A gated recurrent unit (GRU) is combined with a multi-head self-attention network to output both prediction and reconstruction results in a joint optimization strategy, improving the precision of anomaly detection. Extensive experimental studies demonstrate that Meta-MWDG outperforms the state-of-the-art methods in anomaly detection.

Detection and analysis of android malwares using hybrid dual Path bi-LSTM Kepler dynamic graph convolutional network

Detection and analysis of android malwares using hybrid dual Path bi-LSTM Kepler dynamic graph convolutional network

Automatic road network selection method considering functional semantic features of roads with graph convolutional networks

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people’s needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography.

Planar doodles: Their properties, codes and classification

In this paper, we present those properties of planar doodles, especially when regarded as four-valent graphs, that enable us to classify them into prime and super-prime doodles by analogy to a knot sum. We describe a method for partially characterizing a doodle diagram by a doodle code that describes the complementary regions of the diagram and use that code to enumerate all possible prime and super-prime doodle diagrams via their dual graph. In addition, we explore the relationship between planar doodles and twin groups, and note that a theorem of Tutte means that super-prime doodles have a Hamiltonian circuit and we give examples of prime doodles without a Hamiltonian circuit.

Predicting potential microbe-disease associations based on dual branch graph convolutional network.

Studying the association between microbes and diseases not only aids in the prevention and diagnosis of diseases, but also provides crucial theoretical support for new drug development and personalized treatment. Due to the time-consuming and costly nature of laboratory-based biological tests to confirm the relationship between microbes and diseases, there is an urgent need for innovative computational frameworks to anticipate new associations between microbes and diseases. Here, we propose a novel computational approach based on a dual branch graph convolutional network (GCN) module, abbreviated as DBGCNMDA, for identifying microbe-disease associations. First, DBGCNMDA calculates the similarity matrix of diseases and microbes by integrating functional similarity and Gaussian association spectrum kernel (GAPK) similarity. Then, semantic information from different biological networks is extracted by two GCN modules from different perspectives. Finally, the scores of microbe-disease associations are predicted based on the extracted features. The main innovation of this method lies in the use of two types of information for microbe/disease similarity assessment. Additionally, we extend the disease nodes to address the issue of insufficient features due to low data dimensionality. We optimize the connectivity between the homogeneous entities using random walk with restart (RWR), and then use the optimized similarity matrix as the initial feature matrix. In terms of network understanding, we design a dual branch GCN module, namely GlobalGCN and LocalGCN, to fine-tune node representations by introducing side information, including homologous neighbour nodes. We evaluate the accuracy of the DBGCNMDA model using five-fold cross-validation (5-fold-CV) technique. The results show that the area under the receiver operating characteristic curve (AUC) and area under the precision versus recall curve (AUPR) of the DBGCNMDA model in the 5-fold-CV are 0.9559 and 0.9630, respectively. The results from the case studies using published experimental data confirm a significant number of predicted associations, indicating that DBGCNMDA is an effective tool for predicting potential microbe-disease associations.

Kramers-Wannier Duality and Random-Bond Ising Model.

We present a new combinatorial approach to the Ising model incorporating arbitrary bond weights on planar graphs. In contrast to existing methodologies, the exact free energy is expressed as the determinant of a set of ordered and disordered operators defined on a planar graph and the corresponding dual graph, respectively, thereby explicitly demonstrating the Kramers-Wannier duality. The implications of our derived formula for the Random-Bond Ising Model are further elucidated.

Dicritical foliations and semiroots of plane branches

In this work we describe dicritical foliations in (ℂ2,0) at a triple point of the resolution dual graph of an analytic plane branch C using its semiroots. In particular, we obtain a constructive method to present a one-parameter family Cu of separatrices for such foliations. As a by-product we relate the contact order between a special member of Cu and C with analytic discrete invariants of plane branches.

Exploring Generalizable Distillation for Efficient Medical Image Segmentation.

Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks (i.e., teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks.

Mesh Neural Networks Based on Dual Graph Pyramids.

Deep neural networks (DNNs) have been widely used for mesh processing in recent years. However, current DNNs can not process arbitrary meshes efficiently. On the one hand, most DNNs expect 2-manifold, watertight meshes, but many meshes, whether manually designed or automatically generated, may have gaps, non-manifold geometry, or other defects. On the other hand, the irregular structure of meshes also brings challenges to building hierarchical structures and aggregating local geometric information, which is critical to conduct DNNs. In this paper, we present DGNet, an efficient, effective and generic deep neural mesh processing network based on dual graph pyramids; it can handle arbitrary meshes. First, we construct dual graph pyramids for meshes to guide feature propagation between hierarchical levels for both downsampling and upsampling. Second, we propose a novel convolution to aggregate local features on the proposed hierarchical graphs. By utilizing both geodesic neighbors and euclidean neighbors, the network enables feature aggregation both within local surface patches and between isolated mesh components. Experimental results demonstrate that DGNet can be applied to both shape analysis and large-scale scene understanding. Furthermore, it achieves superior performance on various benchmarks, including ShapeNetCore, HumanBody, ScanNet and Matterport3D. Code and models will be available at https://github.com/li-xl/DGNet.

An intricate balancing act: Upstream and downstream frameshift co-regulatory elements.

Targeting ribosomal frameshifting has emerged as a potential therapeutic intervention strategy against Covid-19. During ribosomal translation, a fraction of elongating ribosomes slips by one base in the 5' direction and enters a new reading frame for viral protein synthesis. Any interference with this process profoundly affects viral replication and propagation. For Covid-19, two RNA sites associated with ribosomal frameshifting for SARS-CoV-2 are positioned on the 5' and 3' of the frameshifting residues. Although much attention has been on the 3' frameshift element (FSE), the 5' stem-loop (attenuator hairpin, AH) can play a role. The formation of AH has been suggested to occur as refolding of the 3' RNA structure is triggered by ribosomal unwinding. However, the attenuation activity and the relationship between the two regions are unknown. To gain more insight into these two related viral RNAs and to further enrich our understanding of ribosomal frameshifting for SARS-CoV-2, we explore the RNA folding of both 5' and 3' regions associated with frameshifting. Using our graph-theory-based modeling tools to represent RNA secondary structures, "RAG" (RNA- As-Graphs), and conformational landscapes to analyze length-dependent conformational distributions, we show that AH coexists with the 3-stem pseudoknot of the 3' FSE (graph 3_6 in our dual graph notation) and alternative pseudoknot (graph 3_3) but less likely with other 3' FSE alternative folds (such as 3-way junction 3_5). This is because an alternative length-dependent Stem 1 (AS1) can disrupt the FSE pseudoknots and trigger other folds. In addition, we design four mutants for long lengths that stabilize or disrupt AH, AS1 or FSE pseudoknot to illustrate the deduced AH/AS1 roles and favor the 3_5, 3_6 or stem-loop. These mutants further show how a strengthened pseudoknot can result from a weakened AS1, while a dominant stem-loop occurs with a strengthened AS1. These structural and mutational insights into both ends of the FSE in SARS-CoV-2 advance our understanding of the SARS-CoV-2 frameshifting mechanism by suggesting a sequence of length-dependent folds, which in turn define potential therapeutic intervention techniques involving both elements. Our work also highlights the complexity of viral landscapes with length-dependent folds, and challenges in analyzing these multiple conformations.

Dual separated attention-based graph neural network

Graph neural networks (GNNs) offer a viable solution to model the inter-dependencies among labeled and unlabeled samples in a semi-supervised manner. However, their performances can degrade dramatically when the number of labels is extremely limited, which is due to the limitations of typical graph convolutional network design in most existing GNNs, including over-smoothing, difficulty in extending the propagation step, and failure to preserve the distinctiveness of each node. To address the issues, we propose a dual separated attention-based graph neural network (DSA-GNN) to deal with label scarcity in semi-supervised node classification. Firstly, DSA-GNN decouples feature propagation from representation transformation to alleviate the problems of over-smoothing and overfitting. Secondly, DSA-GNN separates self-representation learning from neighbor-representation learning by two feature extractors with different learnable parameters. As a result, the commonality between connected nodes and the distinctiveness of each node can be both preserved. Thirdly, DSA-GNN incorporates an attention-based label propagation mechanism to refine the label prediction of each node, by aggregating label prediction among the neighborhood based on adaptive edge coefficients. The extensive experimental results on the real-world datasets demonstrate the superiority of DSA-GNN for semi-supervised node classification, especially when the observed labels are extremely limited.

An adaptive dual graph convolution fusion network for aspect-based sentiment analysis

An adaptive dual graph convolution fusion network for aspect-based sentiment analysis

Dual space-based fuzzy graphs and orthogonal basis clustering for unsupervised feature selection

Unsupervised feature selection (UFS) takes an important position because gaining the class labels is laborious or even impossible. In the domain of UFS, clustering is a major means to exploit label information. The existing methods either could not model a clear clustering structure or could not utilize the local structure of data. Consequently, a new clustering method in combination with graph learning is proposed in this work. Specifically, for clustering, orthogonal basis clustering is introduced, where orthogonal constraints are imposed on the cluster center matrix and the clustering matrix. The clustering indicator matrix is also imposed by a non-negative constraint. A clearer clustering structure and more independent clustering centers are obtained through these constraints. For local preservation, given that traditional graphs for keeping the local manifold are faced with the problem of imbalanced neighbors, the fuzzy graph is introduced to acquire a robust structure, which is applied to both data space and feature space. The topological structure in these spaces can be well maintained. For the choice of salient features, ℓ2,0-norm regularization is imposed on the projection matrix. The object function is solved alternately. Then, a feature selection algorithm is designed. Experiments are designed and performed on nine real-world data sets. The results attest to the effectiveness of the proposed algorithm compared with other relevant algorithms.

Generating Euler Diagrams Through Combinatorial Optimization

AbstractCan a given set system be drawn as an Euler diagram? We present the first method that correctly decides this question for arbitrary set systems if the Euler diagram is required to represent each set with a single connected region. If the answer is yes, our method constructs an Euler diagram. If the answer is no, our method yields an Euler diagram for a simplified version of the set system, where a minimum number of set elements have been removed. Further, we integrate known wellformedness criteria for Euler diagrams as additional optimization objectives into our method. Our focus lies on the computation of a planar graph that is embedded in the plane to serve as the dual graph of the Euler diagram. Since even a basic version of this problem is known to be NP‐hard, we choose an approach based on integer linear programming (ILP), which allows us to compute optimal solutions with existing mathematical solvers. For this, we draw upon previous research on computing planar supports of hypergraphs and adapt existing ILP building blocks for contiguity‐constrained spatial unit allocation and the maximum planar subgraph problem. To generate Euler diagrams for large set systems, for which the proposed simplification through element removal becomes indispensable, we also present an efficient heuristic. We report on experiments with data from MovieDB and Twitter. Over all examples, including 850 non‐trivial instances, our exact optimization method failed only for one set system to find a solution without removing a set element. However, with the removal of only a few set elements, the Euler diagrams can be substantially improved with respect to our wellformedness criteria.

Alzheimer’s disease diagnosis from multi-modal data via feature inductive learning and dual multilevel graph neural network

Multi-modal data can provide complementary information of Alzheimer’s disease (AD) and its development from different perspectives. Such information is closely related to the diagnosis, prevention, and treatment of AD, and hence it is necessary and critical to study AD through multi-modal data. Existing learning methods, however, usually ignore the influence of feature heterogeneity and directly fuse features in the last stages. Furthermore, most of these methods only focus on local fusion features or global fusion features, neglecting the complementariness of features at different levels and thus not sufficiently leveraging information embedded in multi-modal data. To overcome these shortcomings, we propose a novel framework for AD diagnosis that fuses gene, imaging, protein, and clinical data. Our framework learns feature representations under the same feature space for different modalities through a feature induction learning (FIL) module, thereby alleviating the impact of feature heterogeneity. Furthermore, in our framework, local and global salient multi-modal feature interaction information at different levels is extracted through a novel dual multilevel graph neural network (DMGNN). We extensively validate the proposed method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset and experimental results demonstrate our method consistently outperforms other state-of-the-art multi-modal fusion methods. The code is publicly available on the GitHub website. (https://github.com/xiankantingqianxue/MIA-code.git)