Showing papers on "Graph (abstract data type) published in 2022"
TL;DR: Wang et al. as discussed by the authors proposed a unified dynamic deep spatio-temporal neural network model based on convolutional neural networks and long short-term memory, termed as (DHSTNet) to simultaneously predict crowd flows in every region of a city.
94 citations
TL;DR: A prior-dependent graph (PDG) construction method can achieve substantial performance, which can be deployed in edge computing module to provide efficient solutions for massive data management and applications in AIoT.
71 citations
TL;DR: A novel personalized diagnosis technique is proposed for early Alzheimer’s disease diagnosis via coupling interpretable feature learning with dynamic graph learning into the GCN architecture and outputs competitive diagnosis performance as well as provide interpretability for personalized disease diagnosis.
63 citations
TL;DR: In this paper, the authors summarize knowledge graph-based works that implement drug repurposing and adverse drug reaction prediction for drug discovery, and introduce several representative embedding models to provide a comprehensive understanding of knowledge representation learning.
61 citations
TL;DR: In this article, a multi-modality graph neural network (MAGNN) is proposed to learn from these multimodal inputs for financial time series prediction, which provides investors with a profitable as well as interpretable option and enables them to make informed investment decisions.
47 citations
TL;DR: In this article, a hierarchical graph neural network is proposed to operate on the hierarchical entity-graph and map the tissue structure to tissue functionality, treating the tissue as a hierarchical composition of multiple types of histological entities from fine to coarse level.
37 citations
TL;DR: A novel spatial–temporal graph neural network framework, namely STGNN-TTE, for travel time estimation is proposed, which is significantly superior to several existing methods on the basis of accuracy and efficiency.
35 citations
TL;DR: Taskflow as discussed by the authors is a lightweight task graph-based approach to streamline the building of parallel and heterogeneous applications using an expressive task graph programming model to assist developers in the implementation of parallel/heterogeneous decomposition strategies on a heterogeneous computing platform.
Abstract: Taskflow aims to streamline the building of parallel and heterogeneous applications using a lightweight task graph-based approach. Taskflow introduces an expressive task graph programming model to assist developers in the implementation of parallel and heterogeneous decomposition strategies on a heterogeneous computing platform. Our programming model distinguishes itself as a very general class of task graph parallelism with in-graph control flow to enable end-to-end parallel optimization. To support our model with high performance, we design an efficient system runtime that solves many of the new scheduling challenges arising out of our models and optimizes the performance across latency, energy efficiency, and throughput. We have demonstrated the promising performance of Taskflow in real-world applications. As an example, Taskflow solves a large-scale machine learning workload up to 29% faster, 1.5× less memory, and 1.9× higher throughput than the industrial system, oneTBB, on a machine of 40 CPUs and 4 GPUs. We have opened the source of Taskflow and deployed it to large numbers of users in the open-source community.
34 citations
TL;DR: An end to end computational model based on graph attention network (GANLDA) is proposed to predict associations between lncRNAs and diseases and outperforms than other four state-of-the-art methods in 10-fold cross validation and devono test.
33 citations
TL;DR: A Heterogeneous Graph Transformer Networks (S_HGTNs) suitable for smart contract anomaly detection to detect financial fraud on the Ethereum platform is constructed.
30 citations
TL;DR: In this article, a scalable digital twin of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments.
Abstract: Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.
31 Mar 2022
TL;DR: In this paper, the authors proposed a graph mining algorithm for graph datasets to extract frequent subgraphs, which has proven to be crucial in numerous aspects such as scientific research and computer vision.
Abstract: Nowadays graphical datasets are having a vast amount of applications. As a result, graph mining—mining graph datasets to extract frequent subgraphs—has proven to be crucial in numerous aspects. It ...
TL;DR: A new variational graph auto-encoder algorithm based on the Graph Convolution Network (GCN), which takes into account the boosting influence of joint generative model of graph structure and node attributes on the embedding output, and implements a self-training mechanism through the construction of auxiliary distribution to further enhance the prediction of node categories.
TL;DR: In this article, the authors proposed to transform the features extracted by a pre-trained self-supervised feature extractor into a Gaussian-like distribution to reduce the feature distribution mis-match.
TL;DR: The RA-AGAT architecture is capable of surpassing the previously applicable methods in the prediction and recommendation of stock return ratio and verified the practicality and applicability of the application of graph models in finance.
TL;DR: Zhang et al. as discussed by the authors proposed an event information integration model that integrates event information through multilayer bidirectional long short-term memory (Bi-LSTM) and attention mechanism.
TL;DR: Automatic Text Summarization (ATS) is an important area in Natural Language Processing (NLP) with the goal of shortening a long text into a more compact version by conveying the most important points in a readable form as mentioned in this paper.
TL;DR: This work proposes a novel model Food recommendation with Graph Convolutional Network (FGCN), which exploits ingredient-ingredient, ingredient-recipe, and recipe-user relations deeply and could alleviate the sparsity issue in food recommendation.
TL;DR: In this paper, a graph-based deep semi-supervised framework was proposed for classifying COVID-19 from chest X-rays, which is able to outperform the current leading supervised model with a tiny fraction of the labelled examples.
TL;DR: A new organization form of axle temperature data is proposed, which connects axle temperature measurement points according to their locations so as to form a graph, and the results show that the prediction accuracy and tracking sensitivity are better than other advanced methods.
TL;DR: A novel UFS approach is proposed by integrating local linear embedding (LLE) and manifold regularization constrained in feature subspace into a unified framework, and a tailored iterative algorithm based on Alternative Direction Method of Multipliers (ADMM) is designed to solve the proposed optimization problem.
TL;DR: With the rapid development of online social recommendation system, substantial methods have been proposed and it is shown that social recommendation performs by integrating so-called "smart recommendation" systems.
Abstract: With the rapid development of online social recommendation system, substantial methods have been proposed. Unlike traditional recommendation system, social recommendation performs by integrating so...
TL;DR: A novel graph variational auto-encoder method to extract nodal features of brain functional connections and a new decoder model for the GVAEs network is proposed, which considers the node neighborhood of the reconstructed adjacency matrix.
TL;DR: This work proposes a general framework for learning node representations in a self supervised manner called Graph Constrastive Learning (GraphCL), which learns node embeddings by maximizing the similarity between the nodes representations of two randomly perturbed versions of the same graph.
TL;DR: Wang et al. as discussed by the authors proposed a continuous CRF graph convolution (CRFConv) for point cloud segmentation, which can capture the structure of features well to improve the representation ability of features rather than simply smoothing.
TL;DR: This paper proposes an unsupervised commercial district discovery framework via embedding space clustering on graph convolution networks (GCN2CDD) to solve the problem of commercialDistrict discovery.
Abstract: Modern enterprises attach much attention to the selection of commercial locations. With the rapid development of urban data and machine learning, we can discover the patterns of human mobility with these data and technology to guide commercial district discovery. In this article, we propose an unsupervised commercial district discovery framework via embedding space clustering on graph convolution networks to solve the problem of commercial district discovery. Specifically, the proposed framework aggregates human mobility features according to geographic similarity by graph convolution networks. Based on the graph convolution network embedding space, we apply hierarchical clustering to mine the latent functional regions hidden in different human patterns. Then, with the kernel density estimation, we can obtain the semantic labels for the clustering results to discover commercial districts. Finally, we analyze the multisource data of the Xiaoshan District and Chengdu City, and experiments verify the effectiveness of our framework.
TL;DR: This paper provides a thorough analysis of the influence of using the different SUMO’s traffic demand generation tools on mobility and node connectivity and proposes an automatized tool that facilitates researchers the generation of synthetic traffic based on real data.
TL;DR: In this paper, a meta-path extracted heterogeneous graph neural network (Megnn) is proposed to extract meaningful metapaths in heterogeneous graphs, providing insights about data and explainable conclusions to the model's effectiveness.
Abstract: Heterogeneous graphs with multiple types of nodes and edges are ubiquitous in the real world and possess immense value in many graph-based downstream applications. However, the heterogeneity within nodes and edges in heterogeneous graphs has brought pressing challenges for practical node representation learning. Existing works manually define multiple meta-paths to model the semantic relationships in heterogeneous graphs. Such strategies heavily rely on the quality of domain knowledge and require extensive hand-crafted works. In this paper, we propose a novel Meta-path Extracted heterogeneous Graph Neural Network ( Megnn ) that is capable of extracting meaningful meta-paths in heterogeneous graphs, providing insights about data and explainable conclusions to the model’s effectiveness. Concretely, Megnn leverages heterogeneous convolution to combine different bipartite sub-graphs corresponding to edge types into a new trainable graph structure. By adopting the message passing paradigm of GNNs through trainable convolved graphs, Megnn can optimize and extract effective meta-paths for heterogeneous graph representation learning. To enhance the robustness of Megnn , we leverage multiple channels to yield various graph structures and devise a channel consistency regularizer to enforce the node embeddings learned from different channels to be similar. Extensive experimental results on three datasets not only show the effectiveness of Megnn compared with the state-of-the-art methods, but also demonstrate the favorable interpretability of the extracted meta-paths.
TL;DR: A novel two-stage embedding model (TSEM), which adequately leverage item multimodal auxiliary information to substantially improve recommendation performance and significantly outperforms the state-of-the-art baselines in terms of various evaluation metrics.
TL;DR: In recent years, advances in Graph Convolutional Networks (GCNs) have given new insights into the development of social recommendation, but many existing GCN-based social recommendation method...
Abstract: In recent years, advances in Graph Convolutional Networks (GCNs) have given new insights into the development of social recommendation. However, many existing GCN-based social recommendation method...