Hierarchical Graph Research Articles

TBM construction risk analysis based on fuzzy Bayesian network

ABSTRACT Aiming at the characteristics of various TBM construction risk factors, fuzzy and complex systems, and frequent shutdown accidents, a TBM construction risk analysis methodology based on a fuzzy Bayesian network is proposed. This method mainly selects eighteen risk factors to construct an interpretive structural model. These factors affect the TBM construction from the four aspects of the geological risk, equipment risk, management risk, and technical risk encountered during the construction of a full-face mechanical excavation of the tunnel. A five-level hierarchical directed graph is extracted by matrix operation to determine the relationship between factors. In the case of incomplete data, the Bayesian network model can be established by employing the prior probability to describe the state of the root node through expert scoring, ideal for system predictions lacking data. Finally, the main risk factors affecting the TBM construction are introduced and discussed, and the TBM construction of the West Second Tunnel of the Beijing Water Supply Phase II Project is taken as an example to compare the evaluation results with those of the actual construction status. The obtained results are not much different from those of the actual situation, which proves that the proposed method is scientific and can provide a reliable basis for analogous projects.

An intelligent inspection method for body-in-white weld quality based on vibration excitation response signals

To enhance the assembly quality in Body-in-White (BIW) assembly, this paper proposes an intelligent detection method for the nugget quality of Resistance Spot Weld (RSW) based on weld joint vibration excitation response signals. The method proposes a novel deep learning model, the Local-Global Hierarchical Graph Neural Network (LGHGNN). LGHGNN can automatically construct graph structures and, by introducing a newly designed upgrade pooling operation, extends the traditional flat structure of graph networks into a hierarchical structure within three-dimensional space. Therefore, LGHGNN achieves layered interaction of local-global information, enabling the model to focus on local details while gaining a broader learning perspective. Additionally, this paper proposes a strategy for multi-label unsupervised anomaly detection that involves layered interaction and collaborative decision-making for local and global graphs. The effectiveness of LGHGNN is demonstrated through its application in the BIW right front door assembly, achieving a remarkable 97.5% average accuracy in multi-region parallel anomaly detection.

Facial augmented reality based on hierarchical optimization of similarity aspect graph

BackgroundThe existing face matching method requires a point cloud to be drawn on the real face for registration, which results in low registration accuracy due to the irregular deformation of the patient's skin that makes the point cloud have many outlier points. MethodsThis work proposes a non-contact pose estimation method based on similarity aspect graph hierarchical optimization. The proposed method constructs a distance-weighted and triangular-constrained similarity measure to describe the similarity between views by automatically identifying the 2D and 3D feature points of the face. A mutual similarity clustering method is proposed to construct a hierarchical aspect graph with 3D pose as nodes. A Monte Carlo tree search strategy is used to search the hierarchical aspect graph for determining the optimal pose of the facial 3D model, so as to realize the accurate registration of the facial 3D model and the real face. ResultsThe proposed method was used to conduct accuracy verification experiments on the phantoms and volunteers, which were compared with four advanced pose calibration methods. The proposed method obtained average fusion errors of 1.13 ± 0.20 mm and 0.92 ± 0.08 mm in head phantom and volunteer experiments, respectively, which exhibits the best fusion performance among all comparison methods. ConclusionsOur experiments proved the effectiveness of the proposed pose estimation method in facial augmented reality.

Hierarchical relationship modeling in multi-agent reinforcement learning for mixed cooperative–competitive environments

In multi-agent reinforcement learning (MARL), information fusion through relationship modeling can effectively learn behavior strategies. However, the high dynamics among heterogeneous interactive agents in mixed cooperative–competitive environments pose difficulties for relational modeling. Traditional MARL solutions concatenate all agents’ states based on the global relationship, which is unrealistic and unscalable under large-scale conditions. Other methods fuse local information by modeling neighbor relationships, but local features lead to suboptimal strategies. From this perspective, we propose a novel relational information fusion approach for mixed tasks to fuse local and global features by modeling heterogeneous relationships through a hierarchical graph. During training, remote agents’ global features are fused through second-order graph representation to help strategy optimization. During decision making, the practicality and scalability of strategy are improved by fusing neighbor agents’ local features through first-order graph representation. Our approach consistently outperforms the state-of-the-art MARL methods in several multi-agent tasks, such as the Predator–Prey and Soccer Games. In particular, it achieves an 83.7% win rate, which is 11.5% higher than baselines in the 4 vs. 4 Soccer Game, and can scale from 4 vs. 4 to 13 vs. 13 in the Predator–Prey Game while maintaining good performance.

Hierarchical graph contrastive learning of local and global presentation for multimodal sentiment analysis

Multi-modal sentiment analysis (MSA) aims to regress or classify the overall sentiment of utterances through acoustic, visual, and textual cues. However, most of the existing efforts have focused on developing the expressive ability of neural networks to learn the representation of multi-modal information within a single utterance, without considering the global co-occurrence characteristics of the dataset. To alleviate the above issue, in this paper, we propose a novel hierarchical graph contrastive learning framework for MSA, aiming to explore the local and global representations of a single utterance for multimodal sentiment extraction and the intricate relations between them. Specifically, regarding to each modality, we extract the discrete embedding representation of each modality, which includes the global co-occurrence features of each modality. Based on it, for each utterance, we build two graphs: local level graph and global level graph to account for the level-specific sentiment implications. Then, two graph contrastive learning strategies is adopted to explore the different potential presentations based on graph augmentations respectively. Furthermore, we design a cross-level comparative learning for learning local and global potential representations of complex relationships.

A fast path relinking algorithm for the min–max edge crossing problem

The min–max edge crossing problem (MMECP) is a challenging and important problem arising in integrated-circuit design, information visualization, and software engineering. Drawing edges as straight lines in accordance with the hierarchical graph drawing standard, the goal is to reduce the maximum number of edge crossings in graphs. In this study, we propose a fast path relinking (FPR) method based on dynamic-programming local search to tackle the MMECP, where an efficient neighborhood reduction mechanism is employed to evaluate only the so-called critical vertices instead of all the vertices. Moreover, the proposed FPR can simultaneously manage a number of neighborhood moves at each search iteration, which is significantly different from all the previous approaches based on one neighborhood in the literature. Extensive computational experiments on MMECP instances show that our proposed FPR approach is relatively competitive compared to the best-performing heuristics and the optimization Gurobi solver. In particular, our algorithm improved the best-known solutions for 104 of the 301 publicly available benchmark instances. Additional experiments were conducted to elucidate the key elements and search parameters of the proposed FPR. Furthermore, we made the source code of the algorithm publicly available to facilitate its use in real applications and future research.

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

Online Fault Diagnosis of Harmonic Drives Using Semisupervised Contrastive Graph Generative Network via Multimodal Data

Harmonic drive is a core component of the industrial robot, its failure will directly affect the robot's performance. Moreover, as the harmonic drive often works with excessive speed and load, it may fail unpredictably. Therefore, online fault diagnosis is quite significant. In this paper, we propose an online intelligent fault diagnosis method for harmonic drives using a Semi-supervised Contrastive Graph Generative Network (SCGGN) via multimodal data. First, multimodal data (including motor current signals and encoder signals) of the harmonic drive are collected online. The Euclidean distance is used to analyze the similarity of the data in the frequency domain. Second, Multiple Graph Convolution Network (MGCN) and Hierarchical Graph Convolution Network (HGCN) are used to obtain complementary fault features from local and global views, respectively. Third, the Contrastive Learning Network is constructed to obtain high-level information through unsupervised learning and perform data clustering to obtain the multi-classification output. Finally, a combination of learnable loss functions is used to optimize the SCGGN. The presented method is tested on an industrial robot. The experimental results show that the method can achieve 86.15% accuracy with 8% of the labeled training data and 79.9% accuracy with only 0.5% of the labeled training data, which is superior to the existing methods.

Feature selection of microarray data using multidimensional graph neural network and supernode hierarchical clustering

Cancer remains a significant cause of mortality, and the application of microarray technology has opened new avenues for cancer diagnosis and treatment. However, due to the challenges in sample acquisition, the genetic dimension of microarray data surpasses the sample dimension, resulting in high-dimensional small sample data. Effective feature selection is crucial for identifying biomarkers and facilitating further analysis. However, existing methods struggle to fully exploit the interdependencies among genes, such as regulatory networks and pathways, to guide the feature selection process and construct efficient classification models. In this paper, we propose a novel feature selection algorithm and classification model based on graph neural networks to address these challenges. Our proposed method employs a multidimensional graph to capture intricate gene interactions. We leverage link prediction techniques to enhance the graph structure relationships and employ a multidimensional node evaluator alongside a supernode discovery algorithm based on spectral clustering for initial node filtering. Subsequently, a hierarchical graph pooling technique based on downsampling is used to further refine node selection for feature extraction and model building. We evaluate the proposed method on nine publicly available microarray datasets, and the results demonstrate its superiority over both classical and advanced feature selection techniques in various evaluation metrics. This highlights the effectiveness and advancement of our proposed approach in addressing the complexities associated with microarray data analysis and cancer classification.

Statement-Grained Hierarchy Enhanced Code Summarization

Code summarization plays a vital role in aiding developers with program comprehension by generating corresponding textual descriptions for code snippets. While recent approaches have concentrated on encoding the textual and structural characteristics of source code, they often neglect the global hierarchical features, causing limited code representation. Addressing this gap, our paper introduces the statement-grained hierarchy enhanced Transformer model (SHT), a novel framework that integrates global hierarchy, syntax, and token sequences to automatically generate summaries for code snippets. SHT is distinctively designed with two encoders to learn both hierarchical and sequential features of code. One relational attention encoder processes the statement-grained hierarchical graph, producing hierarchical embeddings. Subsequently, another sequence encoder integrates these hierarchical structures with token sequences. The resulting enriched representation is then fed into a vanilla Transformer decoder, which effectively generates concise and informative summarizations. Our extensive experiments demonstrate that SHT significantly outperforms state-of-the-art approaches on two widely used Java benchmarks. This underscores the effectiveness of incorporating global hierarchical information in enhancing the quality of code summarizations.

Hierarchical Perceptual Graph Attention Network for Knowledge Graph Completion

Knowledge graph completion (KGC), the process of predicting missing knowledge through known triples, is a primary focus of research in the field of knowledge graphs. As an important graph representation technique in deep learning, graph neural networks (GNNs) perform well in knowledge graph completion, but most existing graph neural network-based knowledge graph completion methods tend to aggregate neighborhood information directly and individually, ignoring the rich hierarchical semantic structure of KGs. As a result, how to effectively deal with multi-level complex relations is still not well resolved. In this study, we present a hierarchical knowledge graph completion technique that combines both relation-level and entity-level attention and incorporates a weight matrix to enhance the significance of the embedded information under different semantic conditions. Furthermore, it updates neighborhood information to the central entity using a hierarchical aggregation approach. The proposed model enhances the capacity to capture hierarchical semantic feature information and is adaptable to various scoring functions as decoders, thus yielding robust results. We conducted experiments on a public benchmark dataset and compared it with several state-of-the-art models, and the experimental results indicate that our proposed model outperforms existing models in several aspects, proving its superior performance and validating the effectiveness of the model.

Tooth Alignment Network Based on Landmark Constraints and Hierarchical Graph Structure.

Automatic tooth alignment target prediction is vital in shortening the planning time of orthodontic treatments and aligner designs. Generally, the quality of alignment targets greatly depends on the experience and ability of dentists and has enormous subjective factors. Therefore, many knowledge-driven alignment prediction methods have been proposed to help inexperienced dentists. Unfortunately, existing methods tend to directly regress tooth motion, which lacks clinical interpretability. Tooth anatomical landmarks play a critical role in orthodontics because they are effective in aiding the assessment of whether teeth are in close arrangement and normal occlusion. Thus, we consider anatomical landmark constraints to improve tooth alignment results. In this article, we present a novel tooth alignment neural network for alignment target predictions based on tooth landmark constraints and a hierarchical graph structure. We detect the landmarks of each tooth first and then construct a hierarchical graph of jaw-tooth-landmark to characterize the relationship between teeth and landmarks. Then, we define the landmark constraints to guide the network to learn the normal occlusion and predict the rigid transformation of each tooth during alignment. Our method achieves better results with the architecture built for tooth data and landmark constraints and has better explainability than previous methods with regard to clinical tooth alignments.

Predicting lncRNA-disease associations using multiple metapaths in hierarchical graph attention networks

BackgroundMany biological studies have shown that lncRNAs regulate the expression of epigenetically related genes. The study of lncRNAs has helped to deepen our understanding of the pathogenesis of complex diseases at the molecular level. Due to the large number of lncRNAs and the complex and time-consuming nature of biological experiments, applying computer techniques to predict potential lncRNA-disease associations is very effective. To explore information between complex network structures, existing methods rely mainly on lncRNA and disease information. Metapaths have been applied to network models as an effective method for exploring information in heterogeneous graphs. However, existing methods are dominated by lncRNAs or disease nodes and tend to ignore the paths provided by intermediate nodes.MethodsWe propose a deep learning model based on hierarchical graphical attention networks to predict unknown lncRNA-disease associations using multiple types of metapaths to extract features. We have named this model the MMHGAN. First, the model constructs a lncRNA-disease–miRNA heterogeneous graph based on known associations and two homogeneous graphs of lncRNAs and diseases. Second, for homogeneous graphs, the features of neighboring nodes are aggregated using a multihead attention mechanism. Third, for the heterogeneous graph, metapaths of different intermediate nodes are selected to construct subgraphs, and the importance of different types of metapaths is calculated and aggregated to obtain the final embedded features. Finally, the features are reconstructed using a fully connected layer to obtain the prediction results.ResultsWe used a fivefold cross-validation method and obtained an average AUC value of 96.07% and an average AUPR value of 93.23%. Additionally, ablation experiments demonstrated the role of homogeneous graphs and different intermediate node path weights. In addition, we studied lung cancer, esophageal carcinoma, and breast cancer. Among the 15 lncRNAs associated with these diseases, 15, 12, and 14 lncRNAs were validated by the lncRNA Disease Database and the Lnc2Cancer Database, respectively. ConclusionWe compared the MMHGAN model with six existing models with better performance, and the case study demonstrated that the model was effective in predicting the correlation between potential lncRNAs and diseases.

Knowledge Graph-Based Hierarchical Text Semantic Representation

Document representation is the basis of language modeling. Its goal is to turn natural language text that flows into a structured form that can be stored and processed by a computer. The bag-of-words model is used by most of the text-representation methods that are currently available. And yet, they do not consider how phrases are used in the text, which hurts the performance of tasks that use natural language processing later on. Representing the meaning of text by phrases is a promising area of future research, but it is hard to do well because phrases are organized in a hierarchy and mining efficiency is low. In this paper, we put forward a method called hierarchical text semantic representation using the knowledge graph (HTSRKG), which uses syntactic structure features to find hierarchical phrases and knowledge graphs to improve how phrases are evaluated. First, we use CKY and PCFG to build the syntax tree sentence by sentence. Second, we walk through the parse tree using the hierarchical routing process to obtain the mixed phrase semantics in passages. Finally, the introduction of the knowledge graph improves the efficiency of text semantic extraction and the accuracy of text representation. This gives us a solid foundation for tasks involving natural language processing that come after. Extensive testing on actual datasets shows that HTSRKG surpasses baseline approaches with respect to text semantic representation, and the results of a recent benchmarking study support this.

Corporate Credit Ratings Based on Hierarchical Heterogeneous Graph Neural Networks

Corporate Credit Ratings Based on Hierarchical Heterogeneous Graph Neural Networks

Graph Pooling Inference Network for Text-based VQA

Effectively leveraging objects and optical character recognition (OCR) tokens to reason out pivotal scene text is critical for the challenging Text-based Visual Question Answering (TextVQA) task. Graph-based models can effectively capture the semantic relationship among visual entities (objects and tokens) and report remarkable performance in TextVQA. However, previous efforts usually leverage all visual entities and ignore the negative effect of superfluous entities. This article presents a Graph Pooling Inference Network (GPIN), which is an evolutionary graph learning method to purify the visual entities and capture the core semantics. It is observed that the dense distribution of reduplicative objects and the crowd of semantically dependent OCR tokens usually co-exist in the image. Motivated by this, GPIN adopts an adaptive node dropping strategy to dynamically downscale semantically closed nodes for graph evolution and update. To deepen the comprehension of scene text, GPIN is a dual-path hierarchical graph architecture that progressively aggregates the evolved object graph and the evolved token graph semantics into a graph vector that serves as visual cues to facilitate the answer reasoning. It can effectively eliminate object redundancy and enhance the association of semantically continuous tokens. Experiments conducted on TextVQA and ST-VQA datasets show that GPIN achieves promising performance compared with state-of-the-art methods.

Differences in Urban Development in China from the Perspective of Point of Interest Spatial Co-Occurrence Patterns

An imbalance in urban development in China has become a contradiction. Points of Interest (POIs) serve as representations of the spatial distribution of urban functions. Analyzing POI spatial co-occurrence patterns can reveal the agglomeration patterns of urban functions across cities at different levels, providing insights into imbalances in urban development. Using POI data from 297 cities in China, the Word2vec model was employed to model the POI spatial co-occurrence patterns, allowing for the quantification of fine-granular urban functionality. Subsequently, the cities were clustered into five tiers representing different levels of development. An urban hierarchical disparity index and graph were introduced to examine variations in urban functions across different tiers. A significant correlation between POI spatial co-occurrence patterns and the GDP of cities at different levels was demonstrated. This study revealed a notable polarization trend characterized by the development of top-tier cities and lagging tail-end cities. Top-tier cities exhibit advantages in terms of their commercial environments, such as international banks, companies, and transportation facilities. Conversely, tail-end cities face deficiencies in urban infrastructure. It is crucial to coordinate resource allocation and establish sustainable development strategies that foster mutual support between the top-tier and tail-end cities.

Combining intra-risk and contagion risk for enterprise bankruptcy prediction using graph neural networks

Predicting the bankruptcy risk of small and medium-sized enterprises (SMEs) is crucial for making decisions about loans. Existing studies in both finance and AI research fields, however, tend to only consider either the intra-risk or contagion risk of enterprises, ignoring their interactions and combinatorial effects. This study for the first time considers both types of risk and their joint effects in bankruptcy prediction. Specifically, we first propose an enterprise intra-risk encoder based on statistically significant enterprise risk indicators for its intra-risk learning. Then, we propose an enterprise contagion risk encoder based on an enterprise knowledge graph for its contagion risk embedding. In particular, the contagion risk encoder includes both the newly proposed Heterogeneous Hyper-Graph Neural Networks (HHGNN) and Hierarchical Graph Transformer Networks (HGTN). Using these two types of encoders, we design a unified framework to simultaneously capture intra-risk and contagion risk for bankruptcy prediction. To evaluate the model, we collect real-world multi-sources data on SMEs and build a novel benchmark dataset called SMEsD. We provide open access to the dataset, which is expected to further promote research on financial risk analysis. Experiments on SMEsD against twelve state-of-the-art baselines demonstrate the effectiveness of the proposed model for bankruptcy prediction.

Haisor : Human-aware Indoor Scene Optimization via Deep Reinforcement Learning

3D scene synthesis facilitates and benefits many real-world applications. Most scene generators focus on making indoor scenes plausible via learning from training data and leveraging extra constraints such as adjacency and symmetry. Although the generated 3D scenes are mostly plausible with visually realistic layouts, they can be functionally unsuitable for human users to navigate and interact with furniture. Our key observation is that human activity plays a critical role and sufficient free space is essential for human-scene interactions. This is exactly where many existing synthesized scenes fail—the seemingly correct layouts are often not fit for living. To tackle this, we present a human-aware optimization framework Haisor for 3D indoor scene arrangement via reinforcement learning, which aims to find an action sequence to optimize the indoor scene layout automatically. Based on the hierarchical scene graph representation, an optimal action sequence is predicted and performed via Deep Q-Learning with Monte Carlo Tree Search (MCTS), where MCTS is our key feature to search for the optimal solution in long-term sequences and large action space. Multiple human-aware rewards are designed as our core criteria of human-scene interaction, aiming to identify the next smart action by leveraging powerful reinforcement learning. Our framework is optimized end-to-end by giving the indoor scenes with part-level furniture layout including part mobility information. Furthermore, our methodology is extensible and allows utilizing different reward designs to achieve personalized indoor scene synthesis. Extensive experiments demonstrate that our approach optimizes the layout of 3D indoor scenes in a human-aware manner, which is more realistic and plausible than original state-of-the-art generator results, and our approach produces superior smart actions, outperforming alternative baselines.

Visuomotor Navigation for Embodied Robots With Spatial Memory and Semantic Reasoning Cognition.

The fundamental prerequisite for embodied agents to make intelligent decisions lies in autonomous cognition. Typically, agents optimize decision-making by leveraging extensive spatiotemporal information from episodic memory. Concurrently, they utilize long-term experience for task reasoning and foster conscious behavioral tendencies. However, due to the significant disparities in the heterogeneous modalities of these two cognitive abilities, existing literature falls short in designing effective coupling mechanisms, thus failing to endow robots with comprehensive intelligence. This article introduces a navigation framework, the hierarchical topology-semantic cognitive navigation (HTSCN), which seamlessly integrates both memory and reasoning abilities within a singular end-to-end system. Specifically, we represent memory and reasoning abilities with a topological map and a semantic relation graph, respectively, within a unified dual-layer graph structure. Additionally, we incorporate a neural-based cognition extraction process to capture cross-modal relationships between hierarchical graphs. HTSCN forges a link between two different cognitive modalities, thus further enhancing decision-making performance and the overall level of intelligence. Experimental results demonstrate that in comparison to existing cognitive structures, HTSCN significantly enhances the performance and path efficiency of image-goal navigation. Visualization and interpretability experiments further corroborate the promoting role of memory, reasoning, as well as their online learned relationships, on intelligent behavioral patterns. Furthermore, we deploy HTSCN in real-world scenarios to further verify its feasibility and adaptability.