Graph Reconstruction Research Articles

Dual Variational Graph Reconstruction Learning for Social Recommendation

Dual Variational Graph Reconstruction Learning for Social Recommendation

Neural relational and dynamics inference for complex systems

Many complex processes in the real world can be viewed as complex systems and their evolution is governed by underlying nonlinear dynamics. However, one can only access the trajectories of the system without knowing the underlying system structure and dynamics in most cases. To address this challenge, this paper proposes a model called Neural Relational and Dynamics Inference (NRDI) that combines graph neural networks (GNNs) and ordinary differential equation systems (ODEs) to handle both continuous-time dynamics prediction and network topology inference for complex systems. Our model contains two modules: (1) the network inference module, which infers system structure from input system trajectories using GNNs, and (2) the dynamics learning module, which employs GNNs to fit the differential equation system for predicting future trajectories. We tested NRDI’s performance on system trajectory prediction and graph reconstruction separately. Experimental results show that the proposed NRDI outperforms many baseline models on continuous-time complex network dynamics prediction, and can explicitly infer network structures with high accuracy.

Towards attributed graph clustering using enhanced graph and reconstructed graph structure

Attributed graph clustering, leveraging both structural and attribute information, is crucial in various real-world applications. However, current approaches face challenges stemming from the sparsity of graphs and sensitivity to noise in Graph Convolutional Networks (GCNs). Moreover, GCN-based methods are often designed based on the assumption of homophilic graph and ignore heterophilic graph. To address these, we propose a graph clustering method that consists of four phases: graph enhance, graph reconstruction, graph refine, and dual-guidance supervisor module. An enhanced graph module is defined by an auxiliary graph to consider distant relationships in the topology structure to alleviate the limitations of sparse graphs. The graph reconstruction phase includes the creation and integration of homophily and heterophily graphs to achieve graph-agnostic. In graph refine, the auxiliary graph is iteratively improved to enhance the generalization of the representation. In this phase, a subspace clustering module is applied to convert attribute-based embeddings into relationship-based representations. Finally, the extracted graphs are fed to a dual-guidance supervisor module to obtain the final clustering result. Experimental validation on several benchmark datasets demonstrates the efficiency of our model. Meanwhile, the findings offer significant advancements in attributed graph clustering, promising improved applicability in various domains.

IMCSN: An improved neighborhood aggregation interaction strategy for multi-scale contrastive Siamese networks

Graph contrastive learning is an effective method for enhancing graph representation by maximizing the similarity of representations between analogous graphs while minimizing the similarity between dissimilar ones. A common approach to improve the representation capabilities of graphs involves data augmentation, which generates additional training samples through transformations applied to the original graphs. However, traditional data augmentation techniques, such as random deletion of nodes or edges, often compromise the structural integrity of graphs, result in loss of crucial information, and lead to representation instability. To overcome these drawbacks, this study introduces a novel data augmentation paradigm, the integration of directed random noise (IDR), which incorporates controlled random noise to optimize the augmentation objectives. IDR enhances the diversity and robustness of representations without sacrificing the structural integrity of the graphs. This approach significantly improves the performance of graph contrastive learning, avoiding the common issues of graph structure damage and information loss associated with conventional methods. To further refine the model, this paper proposes an improved multiscale contrastive Siamese network framework that employs three Siamese networks to process different views of input graphs. It utilizes cross-network and cross-view contrastive learning objectives to optimize graph representations, leveraging the complementary information between different views to maximize the consistency of representations among similar graphs. This enhancement improves the quality and generalizability of graph representations. Additionally, the introduction of a self-supervised loss function based on graph reconstruction within the loss framework capitalizes on the structural similarity between the original and reconstructed graphs to further refine graph representations. This loss function ensures that the global view retains more structural information from the original graph, thus enhancing the complementarity between the global and local views. The effectiveness and stability of this research framework are demonstrated through node classification tasks and visualizations on six real-world datasets, comparing favorably against existing methods such as MERIT and GraphVAT. The proposed model achieves accuracy improvements of 3.21 % and 3.71 % on the Cora dataset and 1.12 % and 1.42 % on the CiteSeer dataset. Additionally, it ranks first in an average accuracy comparison across six datasets, with scores of 80.6 % and 52.67 %. These results underscore the robustness and efficacy of the proposed model in self-supervised graph representation learning, offering substantial advancements over existing techniques.

Auto-weighted Graph Reconstruction for efficient ensemble clustering

Ensemble clustering (EC) is an important field in data clustering, which aims to combine multiple base clustering results of a given dataset into a single consensus result. Previous studies have shown that one of the effective methods is to convert the base clustering results into a graph partitioning problem. Existing spectral ensemble clustering methods typically obtain a spectral embedding matrix for the graph and then perform k-means, separating the graph construction and clustering tasks into two distinct stages. To address these challenges, we propose a novel and efficient ensemble clustering method named Auto-weighted Graph Reconstruction for efficient ensemble clustering. This method integrates weighted base clusters, consensus distance graph construction, and clustering into a unified framework. A consensus distance graph is constructed, from which a stable and discrete label matrix is derived using spectral clustering. An effective optimization algorithm is then employed to address the resulting problem. Finally, the experimental results on eight real-world datasets verify the effectiveness and superiority of the proposed method.

An algebraic approach to the reconstruction of uniform hypergraphs from their degree sequence

The reconstruction of a (hyper)graph starting from its degree sequence is one of the most relevant among the inverse problems investigated in the field of graph theory. In case of graphs, a feasible solution can be quickly reached, while in case of hypergraphs Deza et al. (2018) proved that the problem is NP-hard even in the simple case of 3-uniform ones. This result opened a new research line consisting in the detection of instances for which a solution can be computed in polynomial time. In this work we deal with 3-uniform hypergraphs, and we study them from a different perspective, exploiting a connection of these objects with partially ordered sets. More precisely, we introduce a simple partially ordered set, whose ideals are in bijection with a subclass of 3-uniform hypergraphs. We completely characterize their degree sequences in case of principal ideals (here a simple fast reconstruction strategy follows), and we furthermore carry on a complete analysis of those degree sequences related to the ideals with two generators. We also consider unique hypergraphs in Dext, i.e., those hypergraphs that do not share their degree sequence with other non-isomorphic ones. We show that uniqueness holds in case of hypergraphs associated to principal ideals, and we provide some examples of hypergraphs in Dext where this property is lost.

Reconstruction of dynamic protein-protein interaction network via graph convolutional network

Traditional studies are mostly based on static protein network models. The highly averaged and idealized static protein network does not represent well this dynamic nature that encompasses different time, place and reaction conditions. Therefore, we propose PreDPPI, a method for convolving dynamic protein-protein interaction networks (PINs) using knowledge graph reconstruction of relational graphs, which achieves better performance in terms of dynamics compared to other methods. We found that the longer the length of timestamps used in reconstructing dynamic PINs, the better the prediction. In addition, we identified three hub genes (NUSAP1, SCG3, and CKAP2L) in dynamic PINs that were shown to be significantly associated with glioma prognosis. In conclusion, this work reconstructed a web-based knowledge graph convolving dynamic PINs and identified three hub genes in the GEO glioma dataset that were confirmed to be highly associated with glioma prognosis.

Semantic-Enhanced Variational Graph Autoencoder for Movie Recommendation: An Innovative Approach Integrating Plot Summary Information and Contrastive Learning Strategy

This study introduces a novel movie recommender system utilizing a Semantic-Enhanced Variational Graph Autoencoder for Movie Recommendation (SeVGAER) architecture. The system harnesses additional information from movie plot summaries scraped from the internet, transformed into semantic vectors via a large language model. These vectors serve as supplementary features for movie nodes in the SeVGAER-based recommender. The system incorporates an encoder-decoder structure, operating on a user-movie bipartite graph, and employs GraphSAGE convolutional layers with modified aggregators as the encoder to extract latent representations of the nodes, and a Multi-Layer Perceptron (MLP) as the decoder to predict ratings with additional graph-based features. To address overfitting and improve model generalization, a novel training strategy is introduced. We employ a random data splitting approach, dividing the dataset into two halves for each training instance. The model then generates outputs on each half of the data, and a new loss function is introduced to ensure consistency between these two outputs, a strategy that can be seen as a form of contrastive learning. The model’s performance is optimized using a combination of this new contrastive loss, graph reconstruction loss, and KL divergence loss. Experiments conducted on the Movielens100k dataset demonstrate the effectiveness of this approach in enhancing movie recommendation performance

Spatial-temporal graph Transformer for object tracking against noise spoofing interference

Achieving accurate object tracking against noise spoofing interference caused by similar backgrounds, similar objects, occlusion, or illumination variations is a challenge, especially since Siamese trackers largely ignore the spatial-temporal and part-level information of object structure. To handle this problem, we present a novel object tracking network with spatial-temporal awareness, which learns the correlation of local feature changes and extracts global spatial-temporal fusion features of the object to prevent noise spoofing interference. Specifically, our tracker integrates an object graph reconstruction representation module and a spatial-temporal graph Transformer module. The graph reconstruction representation module models the object structure and search region as part-to-part graph node correspondences, propagating object information to achieve part-level feature aggregation in the search region. The proposed spatial-temporal graph Transformer module fuses the temporal and spatial features of the object to enhance the contextual features and correlation between temporal and spatial feature variations, recognizing the noise spoofing interference to enhance the tracking performance. Meanwhile, our tracker learns object motion information to improve object state awareness, enhancing tracking accuracy under similar objects interference. Extensive experiments on six public datasets validate that our tracker outperforms related state-of-the-art trackers and achieves accurate tracking results against noise spoofing interference.

OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs.

Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation. We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets' scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC's prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27/33 datasets, with an average improvement of 7.2%-22.9% against the state-of-the-art bioactivity prediction methods. The code and dataset developed in this work are available at github.com/Yueming-Yin/OLB-AC.

Automatic Building Roof Plane Extraction in Urban Environments for 3D City Modelling Using Remote Sensing Data

Delineating and modelling building roof plane structures is an active research direction in urban-related studies, as understanding roof structure provides essential information for generating highly detailed 3D building models. Traditional deep-learning models have been the main focus of most recent research endeavors aiming to extract pixel-based building roof plane areas from remote-sensing imagery. However, significant challenges arise, such as delineating complex roof boundaries and invisible boundaries. Additionally, challenges during the post-processing phase, where pixel-based building roof plane maps are vectorized, often result in polygons with irregular shapes. In order to address this issue, this study explores a state-of-the-art method for planar graph reconstruction applied to building roof plane extraction. We propose a framework for reconstructing regularized building roof plane structures using aerial imagery and cadastral information. Our framework employs a holistic edge classification architecture based on an attention-based neural network to detect corners and edges between them from aerial imagery. Our experiments focused on three distinct study areas characterized by different roof structure topologies: the Stadsveld–‘t Zwering neighborhood and Oude Markt area, located in Enschede, The Netherlands, and the Lozenets district in Sofia, Bulgaria. The outcomes of our experiments revealed that a model trained with a combined dataset of two different study areas demonstrated a superior performance, capable of delineating edges obscured by shadows or canopy. Our experiment in the Oude Markt area resulted in building roof plane delineation with an F-score value of 0.43 when the model trained on the combined dataset was used. In comparison, the model trained only on the Stadsveld–‘t Zwering dataset achieved an F-score value of 0.37, and the model trained only on the Lozenets dataset achieved an F-score value of 0.32. The results from the developed approach are promising and can be used for 3D city modelling in different urban settings.

Discovering consensus regions for interpretable identification of RNA N6-methyladenosine modification sites via graph contrastive clustering.

As a pivotal post-transcriptional modification of RNA, N6-methyladenosine (m6A) has a substantial influence on gene expression modulation and cellular fate determination. Although a variety of computational models have been developed to accurately identify potential m6A modification sites, few of them are capable of interpreting the identification process with insights gained from consensus knowledge. To overcome this problem, we propose a deep learning model, namely M6A-DCR, by discovering consensus regions for interpretable identification of m6A modification sites. In particular, M6A-DCR first constructs an instance graph for each RNA sequence by integrating specific positions and types of nucleotides. The discovery of consensus regions is then formulated as a graph clustering problem in light of aggregating all instance graphs. After that, M6A-DCR adopts a motif-aware graph reconstruction optimization process to learn high-quality embeddings of input RNA sequences, thus achieving the identification of m6A modification sites in an end-to-end manner. Experimental results demonstrate the superior performance of M6A-DCR by comparing it with several state-of-the-art identification models. The consideration of consensus regions empowers our model to make interpretable predictions at the motif level. The analysis of cross validation through different species and tissues further verifies the consistency between the identification results of M6A-DCR and the evolutionary relationships among species.

Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion

Hypergraph captures high-order information in structured data and obtains much attention in machine learning and data mining. Existing approaches mainly learn representations for hypervertices by transforming a hypergraph to a standard graph, or learn representations for hypervertices and hyperedges in separate spaces. In this paper, we propose a hypergraph expansion method to transform a hypergraph to a standard graph while preserving high-order information. Different from previous hypergraph expansion approaches like clique expansion and star expansion, we transform both hypervertices and hyperedges in the hypergraph to vertices in the expanded graph, and construct connections between hypervertices or hyperedges, so that richer relationships can be used in graph learning. Based on the expanded graph, we propose a learning model to embed hypervertices and hyperedges in a joint representation space. Compared with the method of learning separate spaces for hypervertices and hyperedges, our method is able to capture common knowledge involved in hypervertices and hyperedges, and also improve the data efficiency and computational efficiency. To better leverage structure information, we minimize the graph reconstruction loss to preserve the structure information in the model. We perform experiments on both hypervertex classification and hyperedge classification tasks to demonstrate the effectiveness of our proposed method.

Conjunctive block coding for hyperdimensional graph representation

Knowledge Graphs (KGs) have become a pivotal knowledge representation tool in machine learning, not only providing access to existing knowledge but also enabling the discovery of new knowledge through advanced applications. Among the scalable reasoning methods used for such applications, distributed graph embedding approaches, particularly GNNs, have become popular for large-scale graph-related tasks. However, many of these methods have limitations in their interpretability and fail to take into account structural similarity in their representation. Hyperdimensional Computing (HDC), also known as Vector Symbolic Architecture (VSA), addresses this issue by using well-defined cognitive operations on distributed representations of symbolic concepts. This work proposes and evaluates a new vector symbolic graph representation, CLOG, that preserves approximate structural similarity beyond edge correspondence and fundamentally differs from previous methods. The model's effectiveness in graph representation is evaluated through theoretical analysis, graph reconstruction experiments, and link prediction task, highlighting its efficiency and accuracy. This approach significantly advances the field by enhancing the capabilities of HDC in graph representation, representing a notable improvement over existing methods.

Leveraging Semantic Information for Enhanced Community Search in Heterogeneous Graphs

Community search (CS) is a vital research area in network science that focuses on discovering personalized communities for query vertices from graphs. However, existing CS methods mainly concentrate on homogeneous or simple attributed graphs, often disregarding complex semantic information and rich contents carried by entities in heterogeneous graphs (HGs). In this paper, we propose a novel problem, namely the “Semantic Network Oriented Community Search with Meta-Structures in Heterogeneous Graphs (SNCS),” which aims to find dense communities that contain the query vertex, with vertices of the same type sharing similar topics. In response to this new problem, we present a novel approach, also named SNCS, representing the first solution employing meta-structures and topic constraints to tackle community search, leveraging both topological and latent features. To overcome the high-time complexity challenge posed by searching through meta-structures, we introduce a unique graph reconstruction technique. Our proposed method’s superiority is validated through extensive evaluations on real-world datasets. The results demonstrate a significant improvement in the quality of the obtained communities, with increases of 3.5–4.4% in clustering coefficient and 5–11% in density while requiring only 4–46% of the running time when compared with the state-of-the-art methods.

Closeness centrality reconstruction of tree graphs

Closeness centrality reconstruction of tree graphs

Contactless Body Measurement System Using Single Fixed-Point RGBD Camera Based on Pose Graph Reconstruction

Contactless Body Measurement System Using Single Fixed-Point RGBD Camera Based on Pose Graph Reconstruction

Information Recovery-Driven Deep Incomplete Multiview Clustering Network.

Incomplete multiview clustering (IMC) is a hot and emerging topic. It is well known that unavoidable data incompleteness greatly weakens the effective information of multiview data. To date, existing IMC methods usually bypass unavailable views according to prior missing information, which is considered a second-best scheme based on evasion. Other methods that attempt to recover missing information are mostly applicable to specific two-view datasets. To handle these problems, in this article, we propose an information-recovery-driven-deep IMC network, termed as RecFormer. Concretely, a two-stage autoencoder network with self-attention structure is built to synchronously extract high-level semantic representations of multiple views and recover the missing data. Besides, we develop a recurrent graph reconstruction mechanism that cleverly leverages the restored views to promote representation learning and further data reconstruction. Visualization of recovery results are given and sufficient experimental results confirm that our RecFormer has obvious advantages over other top methods.

Associations of neuro-glial network calcium activity with mice movements <i>in vivo</i>

Calcium imaging of nerve activity in the mouse hippocampus provides insights into cell-to-cell interactions [1]. Over time, fluctuations in cellular calcium levels encode distinct brain states during mouse brain imaging. Although synapses connect cells and transmit information, it is challenging to detect the spatiotemporal transmission pathway via calcium imaging of multiple cells due to the complexity of the spatial structure and imaging in a separate focal plane [2]. Reconstruction of the dynamic graph of connections between cells was proposed to overcome this problem. A dynamic graph comprises of individual graphs for each time point. A graph linked to a particular time t is composed of vertices representing cells and edges that depict the transmission of signals between cells at that moment. This paper puts forth 3 approaches for creating networks. The first method considers the overlapping time intervals of calcium events in individual cells [3]. The link is established between the cell with the earlier event and the cell with the later start of the event during the moments when the events occurred simultaneously in separate cells. Alternatively, time intervals between the start of events were taken into account. Potentially connected events that began no later than 2 s were linked, with the edge drawn from the cell depicting the earlier starting event to the second cell. The third technique involved linking sequentially occurring events in distinct cells. The edge is drawn from all active cells at the previous time step to newly activated cells at the subsequent time step. Data analysis is based on an experiment in which a mouse moved along a circular track while the fluorescence of neuronal calcium activity and the mouse’s position were recorded at a frequency of 20 frames per second [4]. A red dot was marked on the mouse’s head to track its position. The reconstructed dynamic graph was compared to the angular coordinate of the mouse on the ring to look for repeating patterns of activity. The racetrack was divided into 20 overlapping sectors, each spanning 36 degrees. The reconstructed networks were then assigned to sectors that aligned with the mouse’s angular position on the track. Next, we estimated the frequency of individual edge repetitions within each network group. Only edges that occurred at least three times were chosen for further analysis. We found repeated activations of various cell pairs that corresponded to clockwise and counterclockwise movement within the same sector. Furthermore, we identified the presence of alternating activation, where activity occurred in the first cell, then the second cell, and then again in the first cell. In addition, we identified complex sequences of 5–6 non-sequential activations, represented as a digraph without cycles, which is typical for single sectors.

Method—Time-Variance In EIS Measurements: The Simple Case of Dilution

Classical analysis of Electrochemical Impedance Spectroscopy (EIS) measurements requires them to be performed on a linear, time-invariant system. Many electrochemical systems are time-variant (battery under charge/discharge, corroding sample). The effect of time-variance on these systems is not easy to study because there is no reference to which the time-variant results could be compared to. In this paper, we perform a simple dilution experiment to illustrate the time-variance on EIS measurements performed in a quiescent solution and at a Rotating Disk Electrode (RDE), in an electrolyte containing the classical K3Fe(CN)6/K4Fe(CN)6 redox couple. Using simulations based on analytical expressions of the Faradaic impedance, experimental parameters are defined. Fitting EIS data using Equivalent Circuit Models (ECM allows us to qualify the errors made when trying to fit time-variant data with time-invariant impedance expressions. Repeated impedance measurements and reconstruction of instantaneous impedance graphs via interpolation allows to reduce the effect of time-variance and improve the fitting quality. Finally, another approach is presented, which consists in fitting the time-variant data by an analytical time-dependent expression of the Faradaic impedance where the concentration evolution and its effect are accounted for.