检索结果-内蒙古大学图书馆

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Navarin, Nicolo Pasa, Luca Gallicchio, Claudio Sperduti, Alessandro Univ Padua Via Trieste 63 I-35121 Padua Italy Univ Pisa Largo Bruno Pontecorvo 3 I-56127 Pisa Italy Univ Trento DISI Trento Italy

ISBN: (纸本)9783031442155;9783031442162

Recent works have proven the feasibility of fast and accurate time series classification methods based on randomized convolutional kernels [5,32]. Concerning graph-structured data, the majority of randomized graph neural networks are based on the Echo State Network paradigm in which single layers or the whole network present some form of recurrence [7,8]. This paper aims to explore a simple form of a randomized graph neural network inspired by the success of randomized convolutions in the 1-dimensional domain. Our idea is pretty simple: implement a nofrills convolutional graph neural network and leave its weights untrained. Then, we aggregate the node representations with global pooling operators, obtaining an untrained graph-level representation. Since there is no training involved, computing such representation is extremely fast. We then apply a fast linear classifier to the obtained representations. We opted for LS-SVM since it is among the fastest classifiers available. We show that such a simple approach can obtain competitive predictive performance while being extremely efficient both at training and inference time.

关键词： Graph Neural Network Graph Convolution Reservoir Computing Structured Data machine learning on graphs Deep Randomized Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised framework for evaluating and explaining structural node embeddings of graphs

引用

JOURNAL OF COMPLEX NETWORKS 2024年第2期12卷 cnae003-cnae003页

作者： Dehghan, Ashkan Siuta, Kinga Skorupka, Agata Betlen, Andrei Miller, David Kaminski, Bogumil Pralat, Pawel Toronto Metropolitan Univ Dept Math 350 Victoria St Toronto ON M5B 2K3 Canada SGH Warsaw Sch Econ Al Niepodleglosci 162 PL-02554 Warsaw Poland Patagona Technol Pickering ON Canada

An embedding is a mapping from a set of nodes of a network into a real vector space. Embeddings can have various aims like capturing the underlying graph topology and structure, node-to-node relationship, or other relevant information about the graph, its subgraphs or nodes themselves. A practical challenge with using embeddings is that there are many available variants to choose from. Selecting a small set of most promising embeddings from the long list of possible options for a given task is challenging and often requires domain expertise. Embeddings can be categorized into two main types: classical embeddings and structural embeddings. Classical embeddings focus on learning both local and global proximity of nodes, while structural embeddings learn information specifically about the local structure of nodes' neighbourhood. For classical node embeddings, there exists a framework which helps data scientists to identify (in an unsupervised way) a few embeddings that are worth further investigation. Unfortunately, no such framework exists for structural embeddings. In this article, we propose a framework for unsupervised ranking of structural graph embeddings. The proposed framework, apart from assigning an aggregate quality score for a structural embedding, additionally gives a data scientist insights into properties of this embedding. It produces information which predefined node features the embedding learns, how well it learns them, and which dimensions in the embedded space represent the predefined node features. Using this information, the user gets a level of explainability to an otherwise complex black-box embedding algorithm.

关键词： graph embeddings structural similarity machine learning on graphs explainable AI node structural embeddings role-based embeddings network representation learning

来源：评论

学校读者我要写书评

暂无评论

Backpropagation-free Graph Neural Networks 22

Backpropagation-free Graph Neural Networks

引用

22nd IEEE International Conference on Data Mining (ICDM)

作者： Pasa, Luca Navarin, Nicolo Erb, Wolfgang Sperduti, Alessandro Univ Padua Dept Math Padua Italy

ISBN: (纸本)9781665450997

We propose a class of neural models for graphs that do not rely on backpropagation for training, thus making learning more biologically plausible and amenable to parallel implementation in hardware. The base component of our architecture is a generalization of Gated Linear Networks which allows the adoption of multiple graph convolutions. Specifically, each neuron is defined as a set of graph convolution filters (weight vectors) and a gating mechanism that, given a node and its topological context, selects the weight vector to use for processing the node's attributes. Two different graph processing schemes are studied, i.e., a message-passing aggregation scheme where the gating mechanism is embedded directly into the graph convolution, and a multi-resolution one where neighbouring nodes at different topological distances are jointly processed by a single graph convolution layer. We also compare the effectiveness of different alternatives for defining the context function of a node, i.e., based on hyper-planes or on prototypes. A theoretical result on the expressiveness of the proposed models is also reported. We experimented our backpropagation-free graph convolutional neural architectures on commonly adopted node classification datasets, and show competitive performances compared to the backpropagation-based counterparts.

关键词： Graph Convolutional Networks Graph Neural Network Deep learning Structured Data machine learning on graphs

来源：评论

学校读者我要写书评

暂无评论

Compact Graph Neural Network Models for Node Classification 22

Compact Graph Neural Network Models for Node Classification

引用

37th Annual ACM Symposium on Applied Computing

作者： Pasa, Luca Navarin, Nicolo Sperduti, Alessandro Univ Padua Dept Math Padua Italy

ISBN: (纸本)9781450387132

Recent research on graph convolutional networks tend to increase the complexity and non-linearity of graph convolution operators. Many of these operators result in models exploiting a huge number of learnable parameters, that have to be tuned during the training phase. This aspect makes the application of these approaches on huge datasets challenging due to the considerable computational time required by the training phase. On the other hand, having a huge number of parameters limits the applicability of the models in many node classification problems, in particular in the semisupervised setting where the number of samples for which the target is known is limited to a few dozen nodes. In this paper, we propose a simple and efficient operator dubbed Compact Multi-head Exponential Graph Convolution (CM-EGC). To limit the number of learnable parameters, the proposed model exploits a compact and structurally meaningful representation of the input node features resorting to truncated SVD matrix decomposition, while the expressiveness of the model is ensured by adopting a multi-head attention-based gating mechanism. We evaluated the CM-EGC on semi-supervised and fully-supervised node classification tasks considering 3 well-known benchmark datasets. The results show that even using an extremely compact model, the classification performance of the proposed approach is comparable and sometimes better than the state of the art.

关键词： Graph Neural Network Graph Convolution Structured Data machine learning on graphs Deep learning

来源：评论

学校读者我要写书评

暂无评论

A computational framework for modeling complex sensor network data using graph signal processing and graph neural networks in structural health monitoring

引用

APPLIED NETWORK SCIENCE 2021年第1期6卷 1-24页

作者： Bloemheuvel, Stefan van den Hoogen, Jurgen Atzmueller, Martin Tilburg Univ Tilburg Netherlands Jheronimus Acad Data Sci SHertogenbosch Netherlands Osnabruck Univ Semant Informat Syst Grp Osnabruck Germany

Complex networks lend themselves for the modeling of multidimensional data, such as relational and/or temporal data. In particular, when such complex data and their inherent relationships need to be formalized, complex network modeling and its resulting graph representations enable a wide range of powerful options. In this paper, we target this-connected to specific machine learning approaches on graphs for Structural Health Monitoring (SHM) from an analysis and predictive (maintenance) perspective. Specifically, we present a framework based on Complex Network Modeling, integrating Graph Signal Processing (GSP) and Graph Neural Network (GNN) approaches. We demonstrate this framework in our targeted application domain of SHM. In particular, we focus on a prominent real-world SHM use case, i. e., modeling and analyzing sensor data (strain, vibration) of a large bridge in the Netherlands. In our experiments, we show that GSP enables the identification of the most important sensors, for which we investigate a set of search and optimization approaches. Furthermore, GSP enables the detection of specific graph signal patterns (i. e., mode shapes), capturing physical functional properties of the sensors in the applied complex network. In addition, we show the efficacy of applying GNNs for strain prediction utilizing this kind of sensor data.

关键词： Complex networks Graph signal processing Sensor data Complex networks for physical infrastructures Structural health monitoring Graph neural networks machine learning on graphs

来源：评论

学校读者我要写书评

暂无评论

SELF-GROWING SPATIAL GRAPH NETWORK FOR CONTEXT-AWARE PEDESTRIAN TRAJECTORY PREDICTION

SELF-GROWING SPATIAL GRAPH NETWORK FOR CONTEXT-AWARE PEDESTR...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Haddad, Sirin Lam, Siew-Kei Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore

ISBN: (纸本)9781665441155

Pedestrian trajectory prediction is an active research area with recent works undertaken to embed accurate models of pedestrians social interactions and their contextual compliance into dynamic spatial graphs. However, existing works rely on spatial assumptions about the scene and dynamics, which entails a significant challenge to adapt the graph structure in unknown environments for an online system. In addition, there is a lack of assessment approach for the relational modeling impact on prediction performance. To fill this gap, we propose Social Trajectory Recommender-Gated Graph Recurrent Neighborhood Network (STR-GGRNN), which uses data-driven adaptive online neighborhood recommendation based on the contextual scene features and pedestrian visual cues. The neighborhood recommendation is achieved by online Nonnegative Matrix Factorization (NMF) to construct the graph adjacency matrices for predicting the pedestrians' trajectories. Experiments based on widely-used datasets show that our method outperforms the state-of-the-art. Our best performing model achieves 12 cm ADE and similar to 15 cm FDE on ETH-UCY dataset.

关键词： machine learning on graphs Tracking Vision and Scene Understanding Nonnegative Matrix Factorization

来源：评论

学校读者我要写书评

暂无评论

Simple Multi-resolution Gated GNN

Simple Multi-resolution Gated GNN

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Pasa, Luca Navarin, NicolO Sperduti, Alessandro Univ Padua Dept Math Padua Italy

ISBN: (纸本)9781728190488

Most Graph Neural Networks (GNNs) proposed in literature tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing a simple linear multi-resolution architecture that implements a multi-head gating mechanism. We assessed the performances of the proposed architecture on node classification tasks. To perform a fair comparison and present significant results, we re-implemented the competing methods from the literature and ran the experimental evaluation considering two different experimental settings with different model selection procedures. The proposed convolution, dubbed Simple Multi-resolution Gated GNN, exhibits state-of-the-art predictive performance on the considered benchmark datasets in terms of accuracy. In addition, it is way more efficient to compute than GAT, a well-known multi-head GNN proposed in literature.

关键词： Graph Neural Network Graph Convolution Structured Data machine learning on graphs Deep learning

来源：评论

学校读者我要写书评

暂无评论

Data Analytics on graphs Part II: Signals on graphs

引用

FOUNDATIONS AND TRENDS IN machine learning 2020年第2-3期13卷 158-331页

作者： Stankovic, Ljubisa Mandic, Danilo Dakovic, Milos Brajovic, Milos Scalzo, Bruno Li, Shengxi Constantinides, Anthony G. Univ Montenegro Podgorica Montenegro Imperial Coll London London England

The area of Data Analytics on graphs deals with information processing of data acquired on irregular but structured graph domains. The focus of Part I of this monograph has been on both the fundamental and higher-order graph properties, graph topologies, and spectral representations of graphs. Part I also establishes rigorous frameworks for vertex clustering and graph segmentation, and illustrates the power of graphs in various data association tasks. Part II embarks on these concepts to address the algorithmic and practical issues related to data/signal processing on graphs, with the focus on the analysis and estimation of both deterministic and random data on graphs. The fundamental ideas related to graph signals are introduced through a simple and intuitive, yet general enough case study of multisensor temperature field estimation. The concept of systems on graph is defined using graph signal shift operators, which generalize the corresponding principles from traditional learning systems. At the core of the spectral domain representation of graph signals and systems is the Graph Fourier Transform (GFT), defined based on the eigendecomposition of both the adjacency matrix and the graph Laplacian. Spectral domain representations are then used as the basis to introduce graph signal filtering concepts and address their design, including Chebyshev series polynomial approximation. Ideas related to the sampling of graph signals, and in particular the challenging topic of data dimensionality reduction through graph subsampling, are presented and further linked with compressive sensing. The principles of time-varying signals on graphs and basic definitions related to random graph signals are next reviewed. Localized graph signal analysis in the joint vertex-spectral domain is referred to as the vertex-frequency analysis, since it can be considered as an extension of classical time-frequency analysis to the graph serving as signal domain. Important aspects of the local gra

关键词： graph theory random data on graphs big data on graphs signal processing on graphs machine learning on graphs graph

来源：评论

学校读者我要写书评

暂无评论

Traffic speed prediction in the Lyon area using DCRNN 11

Traffic speed prediction in the Lyon area using DCRNN

引用

Modeles and Analyse des Reseaux: Approches Mathematiques and Informatiques - 11th Conference on Network Modeling and Analysis, MARAMI 2020

作者： Mensi, Fabio Furno, Angelo Cazabet, Remy ENS de Lyon CNRS IXXI Lyon France Univ. Lyon Univ. Gustave Eiffel LICIT UMR T9401 Lyon France Univ de Lyon CNRS Université Lyon 1 LIRIS UMR5205 Villeurbanne France

来源：评论

学校读者我要写书评

暂无评论

Data Analytics on graphs Part I: graphs and Spectra on graphs

引用

FOUNDATIONS AND TRENDS IN machine learning 2020年第1期13卷 1-157页

The area of Data Analytics on graphs promises a paradigm shift, as we approach information processing of new classes of data which are typically acquired on irregular but structured domains (such as social networks, various ad-hoc sensor networks). Yet, despite the long history of Graph Theory, current approaches tend to focus on aspects of optimisation of graphs themselves rather than on eliciting strategies relevant to the objective application of the graph paradigm, such as detection, estimation, statistical and probabilistic inference, clustering and separation from signals and data acquired on graphs. In order to bridge this gap, we first revisit graph topologies from a Data Analytics point of view, to establish a taxonomy of graph networks through a linear algebraic formalism of graph topology (vertices, connections, directivity). This serves as a basis for spectral analysis of graphs, whereby the eigenvalues and eigenvectors of graph Laplacian and adjacency matrices are shown to convey physical meaning related to both graph topology and higher-order graph properties, such as cuts, walks, paths, and neighborhoods. Through a number of carefully chosen examples, we demonstrate that the isomorphic nature of graphs enables both the basic properties of data observed on graphs and their descriptors (features) to be preserved throughout the data analytics process, even in the case of reordering of graph vertices, where classical approaches fail. Next, to illustrate the richness and flexibility of estimation strategies performed on graph signals, spectral analysis of graphs is introduced through eigenanalysis of mathematical descriptors of graphs and in a generic way. Finally, benefiting from enhanced degrees of freedom associated with graph representations, a framework for vertex clustering and graph segmentation is established based on graph spectral representation (eigenanalysis) which demonstrates the power of graphs in various data association tasks, from image c

关键词： graph theory random data on graphs big data on graphs signal processing on graphs machine learning on graphs graph topology learning systems on graphs vertex-frequency estimation graph neural networks graphs and tensors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：