Topological Information Research Articles

Dynamic Graph Representation Learning via Coupling-Process Model.

Representation learning based on dynamic graphs has received a lot of attention in recent years due to its wide range of application scenarios. Although many discrete or continuous dynamic graph representation learning methods have been proposed, many of them ignore the role of edge types. Through the observation of dynamic graphs in the real world, it is found that the types of various edges are very different in nature. They are roughly divided into two categories according to the frequency of occurrence: evolutive edges that appear infrequently and interactive edges that appear frequently. For both types of edges, we propose a coupling-process model (DyCPM) to capture the dynamic mechanisms of them. The model not only generates low-dimensional embedding vectors of nodes, but also aggregates the structural information and temporal information of two kinds of edges. In particular, we design a neural network parameterized discrete process to depict the change law of the topology of evolutive edges and a neural network parameterized temporal point process (TPP) to characterize the temporal dynamic rule of interactive edges. More importantly, we propose a coupling mechanism to transfer the information of the two processes through a shared embedding matrix and finally generate an embedding matrix that aggregates the topology information and temporal information of the two kinds of edges for the dynamic link prediction task. We evaluate our model and several baselines on real datasets. The experimental results show that our model can better aggregate the topology information and temporal information of the two kinds of edges according to their properties and outperforms several state-of-the-art baselines in the performance of dynamic link prediction.

Data-driven optimal cooperative tracking control for heterogeneous multi-agent systems

This paper presents a novel hierarchical control scheme for solving the data-driven optimal cooperative tracking control problem of heterogeneous multi-agent systems. Considering that followers cannot communicate with the leader, a prescribed-time fully distributed observer is devised to estimate the leader’s state for each follower. Then, the data-driven decentralized controller is designed to ensure that the follower’s output can track the leader’s one. Compared with the existing results, the advantages of the designed distributed observer are that the prescribed convergence time is completely predetermined by the designer, and the design of the observer gain is independent of the global topology information. Besides, the advantages of the designed decentralized controller are that neither the follower’s system model nor a known initial stabilizing control policy is required. Finally, simulation results exemplify the advantage of the proposed method.

Non-local interaction in discrete Ricci curvature-induced biological aggregation

We investigate the collective dynamics of multi-agent systems in two- and three-dimensional environments generated by minimizing discrete Ricci curvature with local and non-local interaction neighbourhoods. We find that even a single effective topological neighbour suffices for significant order in a system with non-local topological interactions. We also explore topological information flow patterns and clustering dynamics using Hodge spectral entropy and mean Forman–Ricci curvature.

Deep time-series clustering via latent representation alignment

In practice, obtaining sufficient label information from a dataset is challenging. Consequently, various clustering methods have been studied to homogeneously group data without label information. Recently, deep clustering approaches that utilize deep neural networks have garnered considerable attention. However, time series data possess unique characteristics, including temporal relationships between observations in a sequence, which can decrease the performance of existing deep clustering methods when applied to time series. Despite this, few studies on deep clustering have addressed the characteristics of time series. Thus, we propose a novel approach for deep time-series clustering using topological information, enabling the capture of underlying temporal patterns to generate cluster-oriented representations. We address the topological information of a time series by introducing a novel loss function based on the eigendecomposition of representations in latent space. Through experiments on various time-series datasets, we demonstrate the efficacy of the proposed method in achieving superior clustering performance compared to state-of-the-art deep clustering methods. To the best of our knowledge, this is the first approach that utilizes topological information for deep time-series clustering.

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.

Heterogeneous-branch integration framework: Introducing first-order predicate logic in Logical Reasoning Question Answering

The logical reasoning question-answering is a critical task in natural language processing, as it equips models with human-like logical reasoning intelligence. Existing approaches focus on extracting and leveraging the hidden logical structures within text. However, previous works explore partial logical relationships and neglect the holistic extraction within the text. Moreover, they struggle to fully model logical connections, including long-distance dependencies and local topology information. To address these issues, we propose a novel heterogeneous-branch integration framework. Our framework is based on first-order predicate logic theory and consists of three primary components. First, we construct two heterogeneous logical graphs to model logical relationships within and between propositions. Second, we propose a novel Graph-Masked Transformer with a novel graph-masked multi-head attention mechanism to enable distant node interactions and local sparse relationship modeling. Third, we propose a novel multi-branch fusion module to integrate information from multiple sources and generate answer predictions. The proposed heterogeneous-branch integration framework outperforms the VDGN method by 2.73% in accuracy on the ReClor dataset and 2.15% on the LogiQA dataset. Our code and models will be made available at https://github.com/starry-y/HBI.

Direct numerical simulation of a subcritical coaxial injection in fiber regime using sharp interface reconstruction

The numerical simulation of space launchers combustion chambers is a topic of increasing interest, as it may help the development of safer and more efficient designs. Understanding fuel injection is a particularly severe challenge. The liquid oxygen is injected by a round orifice surrounded by an annular gaseous stream of fuel, leading in subcritical conditions to a two-phase assisted atomization process. The result of this process is a very dense and polydisperse two-phase flow, which strongly influences the behavior of the chamber. Experimental investigation of this flow is difficult due to the axisymmetric geometry and the dense characteristic of the spray. Neither RANS nor Large Eddy Simulation (LES) possess reliable models able to reproduce the smallest scales of atomization, one of the reasons being the lack of relevant experimental data. Therefore, this work aims to provide detailed information on the atomization process using Direct Numerical Simulation. This paper presents a Direct Numerical Simulation (DNS) of a coaxial liquid–gas assisted atomization in the typical fiber regime encountered in cryogenic injectors. This study aims to better understand the evolution of liquid topology and extract relevant information that may help develop larger-scale models. The flow was first analyzed in terms of topology statistical data, using a dedicated detection and classification algorithm that could characterize the individual liquid structures. These include the central liquid core, the ligament created during primary atomization, and the spherical droplet obtained at the end of the atomization process. Subsequently, a more global statistical topology indicator was investigated, namely the interface area density distribution. This quantity is used in larger-scale RANS or LES models to predict the smallest scales of atomization. Therefore, understanding its behavior in a realistic case is of utmost importance. The interface area density distribution was correlated to the global jet behavior and the liquid topology data obtained by the detection algorithm. The results showed, in particular, a strong correlation between the initial increase of liquid–gas interface area density with the generation of ligaments and between the continuous decrease of the interface area density during droplet formation and stabilization.

BCNet: Bronchus Classification via Structure Guided Representation Learning.

CT-based bronchial tree analysis is a key step for the diagnosis of lung and airway diseases. However, the topology of bronchial trees varies across individuals, which presents a challenge to the automatic bronchus classification. To solve this issue, we propose the Bronchus Classification Network (BCNet), a structure-guided framework that exploits the segment-level topological information using point clouds to learn the voxel-level features. BCNet has two branches, a Point-Voxel Graph Neural Network (PV-GNN) for segment classification, and a Convolutional Neural Network (CNN) for voxel labeling. The two branches are simultaneously trained to learn topology-aware features for their shared backbone while it is feasible to run only the CNN branch for the inference. Therefore, BCNet maintains the same inference efficiency as its CNN baseline. Experimental results show that BCNet significantly exceeds the state-of-the-art methods by over 8.0% both on F1-score for classifying bronchus. Furthermore, we contribute BronAtlas: an open-access benchmark of bronchus imaging analysis with high-quality voxel-wise annotations of both anatomical and abnormal bronchial segments. The benchmark is available at link1.

Dynamic attention aggregated missing spatial–temporal data imputation for traffic speed prediction

Traffic speed forecasting is indispensable in Intelligent Traffic Systems (ITS). The missing traffic speed due to sensors’ failure may hamper the accurate prediction of traffic speed. Different kinds of imputation techniques were employed to replace the missing values considering the spatial and temporal information. However, previous techniques did not consider the dynamic contribution of the neighboring nodes and failed to capture the complex properties of traffic speed data precisely. The architecture of the previous imputation models was infeasible in real-time applications in terms of scalability. Therefore, a novel machine learning-based imputation technique is proposed to generate the missing traffic speed using the spatial–temporal information and dynamic contribution of neighboring nodes. A new dataset considering the characteristics of the traffic speed data is generated from the existing dataset by exploiting the non-missing traffic speed of neighboring nodes. The newly formed dataset helps in the estimation of the dynamic contribution of the neighboring nodes using the linear regression algorithm. The non-missing speeds and estimated dynamic contribution of neighboring nodes assist in calculating the missing speeds of a node. Furthermore, a novel deep learning-based prediction model is introduced to forecast traffic speed accurately. The prediction model contains graph structure learning, a deep graph neural network with skip connections, GRU, multi-head soft attention, and a fully connected neural network. Graph structure learning is proposed based on the distribution of the congestion to represent the graph in an efficient way. The deep graph neural network with skip connections and GRU help in capturing topological and temporal information, respectively. The multi-head soft attention is designed to focus on every relevant temporal information at each time step for capturing global traffic information. Finally, the extracted spatial–temporal features are fed into the fully connected neural network to predict the traffic speed. The proposed imputation and prediction models are evaluated on two real-time datasets, METR-LA and PeMSD7 datasets, under different missing rates of different missing patterns. The proposed framework generates possible spatial–temporal information for efficient traffic congestion management and evicts erroneous issues in real-time.

A unified framework of semi-supervised community detection integrating network topology and node content

Detecting the community structure within networks is important because it aids in the analysis of complex networks. However, the existence of diverse complex structures in the network topology can limit the topological information’s ability to represent communities. For instance, the accuracy of many traditional methods based on topology alone decreases sharply when a link is missing or noisy. To solve the above-mentioned issues simultaneously, we propose a unified framework of semi-supervised community detection integrating content information. Three models are proposed, instead of a special model-handling problem. The framework used performs the same interpretation for a target problem. The inputs contain the adjacent and node content matrix. The proposed models describe the network topology using a non-negative matrix factorization (NMF) algorithm–based generative model or modularity maximization algorithm. Additionally, we use the equivalence theory of the pLSI, and NMF models the content information based on NMF. Community membership is also used as the relationship between communities and node contents. The models uniformly integrate content information and network topology. Further, a constraint matrix that depicts must-links is built by calculating the similarity of neighbors between any two nodes. Must-link pairs can represent the network topology’s prior information. The models’ community memberships are adjusted by using a strong constraint based on the connected component of this matrix. The models also introduce prior information into the topological and content information in the mentioned models. We compared the proposed models with the state-of-the-art community detection models on artificial networks and five real networks. The experimental results show that the proposed models outperformed the models combining topology and content and semi-supervised models. Fusing the topology with the content and the prior information in the models was also effective for community detection. Thus, the models under the framework are more advantageous than other semi-supervised models when incorporating the same amount of prior information into the models. The semi-supervised framework used also has a certain level of competitiveness in detecting communities.

Anomalous behavior detection based on optimized graph embedding representation in social networks

Anomalous behaviors in social networks can lead to privacy leaks and the spread of false information. In this paper, we propose an anomalous behavior detection method based on optimized graph embedding representation. Specifically, the user behavior logs are first extracted into a social network user behavior temporal knowledge graph, based on which the graph embedding representation method is used to transform the network topology and temporal information in the user behavior knowledge graph into structural embedding vectors and temporal information embedding vectors, and the hybrid attention mechanism is used to merge the two types of vectors to obtain the final entity embedding to complete the prediction and complementation of the temporal knowledge graph of user behavior. We use graph neural networks, which use the temporal information of user behaviors as a time constraint and capture both user behavioral and semantic information. It converts the two parts of information into vectors for concatenation and linear transformation to obtain a comprehensive representation vector of the whole subgraph, as well as joint deep learning models to evaluate abnormal behavior. Finally, we perform experiments on the Yelp dataset to validate that our method achieves a 9.56% improvement in the F1-score.

RAAFNet: Reverse Attention Adaptive Fusion Network for Large-Scale Point Cloud Semantic Segmentation

Point cloud semantic segmentation is essential for comprehending and analyzing scenes. However, performing semantic segmentation on large-scale point clouds presents challenges, including demanding high memory requirements, a lack of structured data, and the absence of topological information. This paper presents a novel method based on the Reverse Attention Adaptive Fusion network (RAAFNet) for segmenting large-scale point clouds. RAAFNet consists of a reverse attention encoder–decoder module, an adaptive fusion module, and a local feature aggregation module. The reverse attention encoder–decoder module is applied to extract point cloud features at different scales. The adaptive fusion module enhances fine-grained representation within multi-resolution feature maps. Furthermore, a local aggregation classifier is introduced, which aggregates the features of neighboring points to the center point in order to leverage contextual information and enhance the classifier’s perceptual capability. Finally, the predicted labels are generated. Notably, our method excels at extracting point cloud features across different dimensions and produces highly accurate segmentation results. Experimental results on the Semantic3D dataset achieved an overall accuracy of 89.9% and a mIoU of 74.4%.

Temporal subgraph matching method for multi-connected temporal graph

Temporal graph matching is used to find a matching subgraph set that satisfies temporal and topological information on the temporal graph. It is widely used in real scenarios and provides important support for big data mining and analysis. Most existing matching methods take the single-connected graph as the matching graph, which has a high computational cost. Simultaneously, the construction and matching complexity of its index on multi-connected temporal subgraph matching is high. To solve the above problems, we propose a new temporal subgraph matching problem for multi-connected temporal graphs and proposes the corresponding efficient filtering-selecting-matching three-stage multi-connected temporal subgraph matching method. In the filtering stage, a vertex-based filter is proposed to generate a candidate temporal subgraph set. In the select phase, a set of temporal subgraphs satisfying the vertex mapping is found. In the matching stage, the single-filter temporal subgraph matching method and temporal subgraph matching based on the temporal information tree index method are proposed to solve the problems that the edges of multi-connected temporal subgraphs cannot be mapped and the single graph matching efficiency is low, respectively. The experimental results show that the proposed method improves the matching accuracy, and the corresponding index size is reduced.

Influence Maximization Based on Adaptive Graph Convolution Neural Network in Social Networks

The influence maximization problem is a hot issue in the research on social networks due to its wide application. The problem aims to find a small subset of influential nodes to maximize the influence spread. To tackle the challenge of striking a balance between efficiency and effectiveness in traditional influence maximization algorithms, deep learning-based influence maximization algorithms have been introduced and have achieved advancement. However, these algorithms still encounter two key problems: (1) Traditional deep learning models are not well-equipped to capture the latent topological information of networks with varying sizes and structures. (2) Many deep learning-based methods use the influence spread of individual nodes as labels to train a model, which can result in an overlap of influence among the seed nodes selected by the model. In this paper, we reframe the influence maximization problem as a regression task and introduce an innovative approach to influence maximization. The method adopts an adaptive graph convolution neural network which can explore the latent topology information of the network and can greatly improve the performance of the algorithm. In our approach, firstly, we integrate several network-level attributes and some centrality metrics into a vector as the presentation vector of nodes in the social network. Next, we propose a new label generation method to measure the influence of nodes by neighborhood discount strategy, which takes full account of the influence overlapping problem. Subsequently, labels and presentation vectors are fed into an adaptive graph convolution neural network model. Finally, we use the well-trained model to predict the importance of nodes and select top-K nodes as a seed set. Abundant experiments conducted on various real-world datasets have confirmed that the performance of our proposed algorithm surpasses that of several current state-of-the-art algorithms.

Degradation strategies for structural characterization of insoluble synthetic polymers by mass spectrometry.

With the advent of soft ionization techniques such as electrospray (ESI) and matrix-assisted laser desorption/ionization (MALDI) to produce intact gas-phase ions from nonvolatile macromolecules, mass spectrometry has become an essential technique in the field of polymeric materials. However, (co)polymers of very high molecular weight or with reticulated architectures still escape ESI or MALDI, mainly due to solubility issues. Strategies developed to tackle such an analytical challenge all rely on sample degradation to produce low-mass species amenable to existing ionization methods. Yet, chain degradation needs to be partial and controlled to generate sufficiently large species that still contain topological or architectural information. The present article reviews the different analytical degradation strategies implemented to perform mass spectrometry of these challenging synthetic polymers, covering thermal degradation approaches in sources developed in the 2000s, off-line sample pre-treatments for controlled chemical degradation of polymeric substrates, and most recent achievements employing reactive ionization modes to perform chemolysis on-line with MS.

Hand-aware graph convolution network for skeleton-based sign language recognition

Skeleton-based sign language recognition (SLR) is a challenging research area mainly due to the fast and complex hand movement. Currently, graph convolution networks (GCNs) have been employed in skeleton-based SLR and achieved remarkable performance. However, existing GCN-based SLR methods suffer from a lack of explicit attention to hand topology which plays an important role in the sign language representation. To address this issue, we propose a novel hand-aware graph convolution network (HA-GCN) to focus on hand topological relationships of skeleton graph. Specifically, a hand-aware graph convolution layer is designed to capture both global body and local hand information, in which two sub-graphs are defined and incorporated to represent hand topology information. In addition, in order to eliminate the over-fitting problem, an adaptive DropGraph is designed in construction of hand-aware graph convolution block to remove the spatial and temporal redundancy in the sign language representation. With the aim to further improve the performance, the joints information, bones, together with their motion information are simultaneously modeled in a multi-stream framework. Extensive experiments on the two open-source datasets, AUTSL and INCLUDE, demonstrate that our proposed algorithm outperforms the state-of-the-art with a significant margin. Our code is available at https://github.com/snorlaxse/HA-SLR-GCN.

A lightweight attention-based multi-frequency topology learning framework for driving fatigue detection

Driving fatigue has been one of the major causes of traffic accident. Efficient and accurate detection of driving fatigue are a legitimate public concern. In this paper, we conduct the simulated driving experiments and an EEG-based driving fatigue detection framework integrating multilayer brain network and convolutional neural network (CNN) is developed. This lightweight attention-based multi-frequency topology learning (AMFTL) framework first captures the fatigue-related multi-frequency brain topological information and then feeds it into a CNN-based topology feature extraction (TFE) module to fully explore and integrate the critical topological features. The quantitative analysis results show that there are significant differences in brain topologies between the alert and fatigue states. And experimental results show that our proposed framework achieves an average detection accuracy of 94.71% for driving fatigue, which outperforms the current state-of-the-art methods. This proposed framework is expected to open new venues for EEG-based brain state analysis, and holds promising practical application potential.

Fully Flexible Molecular Alignment Enables Accurate Ligand Structure Modeling.

Accurate protein-ligand binding poses are the prerequisites of structure-based binding affinity prediction and provide the structural basis for in-depth lead optimization in small molecule drug design. However, it is challenging to provide reasonable predictions of binding poses for different molecules due to the complexity and diversity of the chemical space of small molecules. Similarity-based molecular alignment techniques can effectively narrow the search range, as structurally similar molecules are likely to have similar binding modes, with higher similarity usually correlated to higher success rates. However, molecular similarity is not consistently high because molecules often require changes to achieve specific purposes, leading to reduced alignment precision. To address this issue, we propose a new alignment method─Z-align. This method uses topological structural information as a criterion for evaluating similarity, reducing the reliance on molecular fingerprint similarity. Our method has achieved success rates significantly higher than those of other methods at moderate levels of similarity. Additionally, our approach can comprehensively and flexibly optimize bond lengths and angles of molecules, maintaining a high accuracy even when dealing with larger molecules. Consequently, our proposed solution helps in achieving more accurate binding poses in protein-ligand docking problems, facilitating the development of small molecule drugs. Z-align is freely available as a web server at https://cloud.zelixir.com/zalign/home.

IS-GNN: Graph neural network enhanced by aggregating influential and structurally similar nodes

Nowadays, it has been demonstrated that graph neural networks (GNNs) are a powerful tool for graph representation learning. However, most GNN models are shallow ones because stacking more layers may cause the over-smoothing problem. In addition, conventional neighborhood aggregation GNNs have an implicit homophily assumption, leading to poor performance when dealing with networks with heterophily. To address the aforementioned issues, we present a new GNN model, called IS-GNN, to effectively enhance the representation quality of nodes in general networks. IS-GNN learns the representation of each node using three aspects of information: local structural information from its neighborhood, global topological information from influential nodes, and homophilous information from its structurally similar nodes. Consequently, the representations of nodes are more powerful and discriminative. The effectiveness of IS-GNN is validated on both homophilous and heterophilous networks. The experimental results of semi-supervised node classification manifest that the accuracy of IS-GNN is superior to that of baselines.

Refining computational inference of gene regulatory networks: integrating knockout data within a multi-task framework.

Constructing accurate gene regulatory network s (GRNs), which reflect the dynamic governing process between genes, is critical to understanding the diverse cellular process and unveiling the complexities in biological systems. With the development of computer sciences, computational-based approaches have been applied to the GRNs inference task. However, current methodologies face challenges in effectively utilizing existing topological information and prior knowledge of gene regulatory relationships, hindering the comprehensive understanding and accurate reconstruction of GRNs. In response, we propose a novel graph neural network (GNN)-based Multi-Task Learning framework for GRN reconstruction, namely MTLGRN. Specifically, we first encode the gene promoter sequences and the gene biological features and concatenate the corresponding feature representations. Then, we construct a multi-task learning framework including GRN reconstruction, Gene knockout predict, and Gene expression matrix reconstruction. With joint training, MTLGRN can optimize the gene latent representations by integrating gene knockout information, promoter characteristics, and other biological attributes. Extensive experimental results demonstrate superior performance compared with state-of-the-art baselines on the GRN reconstruction task, efficiently leveraging biological knowledge and comprehensively understanding the gene regulatory relationships. MTLGRN also pioneered attempts to simulate gene knockouts on bulk data by incorporating gene knockout information.