NEXT-BEST-VIEW METHOD BASED ON CONSECUTIVE EVALUATION OF TOPOLOGICAL RELATIONS

This work describes an iterative algorithm for estimating optimal viewpoints, so called next-best-views (NBVs). The goal is to incrementally construct a topological network from the scene during the consecutive acquisition of several views. Our approach is a hybrid method between a surface-based and a volumetric approach with a continuous model space. Hence, a new scan taken from an optimal position should either cover as much as possible from the unknown object surface in one single scan, or densify the existing data and close possible gaps. Based on the point density, we recover the essential and structural information of a scene based on the Growing Neural Gas (GNG) algorithm. From the created graph representation of topological relations, the density of the point cloud at each network node is estimated by approximating the volume of Voronoi cells. The NBV Finder selects a network node as NBV, which has the lowest point density. Our NBV method is self-terminating when all regions reach a predefined minimum point density or the change of the GNG error is zero. For evaluation, we use a Buddha statue with a rather simple surface geometry but still some concave parts and the Stanford Dragon with a more complex object surface containing occluded and concave parts. We demonstrate that our NBV method outperforms a “naive random” approach relying on uniformly distributed sensor positions in terms of efficiency, i.e. our proposed method reaches a desired minimum point density up to 20% faster with less scans.

Download Full-text

NEXT-BEST-VIEW METHOD BASED ON CONSECUTIVE EVALUATION OF TOPOLOGICAL RELATIONS

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xli-b3-11-2016 ◽

2016 ◽

Vol XLI-B3 ◽

pp. 11-19

Author(s):

K. O. Dierenbach ◽

M. Weinmann ◽

B. Jutzi

Keyword(s):

Structural Information ◽

Graph Representation ◽

Minimum Point ◽

Complex Object ◽

Network Node ◽

Object Surface ◽

Surface Geometry ◽

Topological Relations ◽

Optimal Position ◽

Point Density

Download Full-text

DECOMPOSITION METHOD FOR DETERMINING THE HIGH REFLECTED SECTIONS OF A COMPLEX OBJECT SURFACE

Telecommunications and Radio Engineering ◽

10.1615/telecomradeng.v77.i11.20 ◽

2018 ◽

Vol 77 (11) ◽

pp. 945-956 ◽

Cited By ~ 1

Author(s):

N. N. Kolchigin ◽

M. N. Legenkiy ◽

A. A. Maslovskiy ◽

А. Demchenko ◽

S. Vinnichenko ◽

...

Keyword(s):

Decomposition Method ◽

Complex Object ◽

Object Surface

Download Full-text

A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽

10.3390/cancers13092111 ◽

2021 ◽

Vol 13 (9) ◽

pp. 2111

Author(s):

Bo-Wei Zhao ◽

Zhu-Hong You ◽

Lun Hu ◽

Zhen-Hao Guo ◽

Lei Wang ◽

...

Keyword(s):

Drug Target ◽

Large Scale ◽

Computational Models ◽

Structural Information ◽

Characteristic Curve ◽

Representation Learning ◽

Graph Representation ◽

Convolutional Network ◽

Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

Download Full-text

An Attention-Based Graph Neural Network for Heterogeneous Structural Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5833 ◽

2020 ◽

Vol 34 (04) ◽

pp. 4132-4139

Author(s):

Huiting Hong ◽

Hantao Guo ◽

Yucheng Lin ◽

Xiaoqing Yang ◽

Zang Li ◽

...

Keyword(s):

Neural Network ◽

Structural Information ◽

Representation Learning ◽

Graph Representation ◽

Heterogeneous Information ◽

Domain Experts ◽

Proposed Model ◽

Meta Path ◽

Low Dimensional ◽

Public Datasets

In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations. Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN. In this paper, we propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path and achieve more informative representations. With this method, domain experts will not be needed to design meta-path schemes and the heterogeneous information can be processed automatically by our proposed model. Specifically, we implicitly represent heterogeneous information using the following two methods: 1) we model the transformation between heterogeneous vertices through a projection in low-dimensional entity spaces; 2) afterwards, we apply the graph neural network to aggregate multi-relational information of projected neighborhood by means of attention mechanism. We also present three extensions of HetSANN, i.e., voices-sharing product attention for the pairwise relationships in HIN, cycle-consistency loss to retain the transformation between heterogeneous entity spaces, and multi-task learning with full use of information. The experiments conducted on three public datasets demonstrate that our proposed models achieve significant and consistent improvements compared to state-of-the-art solutions.

Download Full-text

From Geons to Structure. A Note on Object Representation

Perception ◽

10.1068/p230505 ◽

1994 ◽

Vol 23 (5) ◽

pp. 505-515 ◽

Cited By ~ 20

Author(s):

Emanuel Leeuwenberg ◽

Peter Van der Helm ◽

Rob Van Lier

Keyword(s):

Information Theory ◽

Object Representation ◽

Structural Information ◽

Object Classification ◽

Object Perception ◽

Complex Object ◽

Object Representations ◽

Perceptual Process

Two models of object perception are compared: recognition by components (RBC), proposed by Biederman, and structural information theory (SIT), initially proposed by Leeuwenberg. According to RBC a complex object is decomposed into predefined elementary objects, called geons. According to SIT, the decomposition is guided by regularities in the object. It is assumed that the simplest of all possible interpretations of any object is perceptually preferred. The comparison deals with two aspects of the models. One is the representation of simple objects—various definitions of object axes are considered. It is shown that the more these definitions account for object regularity and thus the more they agree with SIT, the better the object representations predict object classification. Another topic concerns assumptions underlying the models: the identification of geons is mediated by cues which are supposed to be invariant under varying viewpoints of objects. It is argued that such cues are not based on this invariance but on the regularity of actual objects. The latter conclusion is in line with SIT. An advantage of RBC, however, is that it deals with the perceptual process from stimulus to interpretation, whereas SIT merely concerns the outcome of the process, not the process itself.

Download Full-text

Adversarial Deep Network Embedding for Cross-Network Node Classification

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i03.5692 ◽

2020 ◽

Vol 34 (03) ◽

pp. 2991-2999 ◽

Cited By ~ 1

Author(s):

Xiao Shen ◽

Quanyu Dai ◽

Fu-lai Chung ◽

Wei Lu ◽

Kup-Sze Choi

Keyword(s):

Domain Adaptation ◽

Structural Information ◽

Classification Problem ◽

Network Node ◽

Network Embedding ◽

Deep Network ◽

Network Applications ◽

Target Network ◽

Node Classification ◽

Learn Network

In this paper, the task of cross-network node classification, which leverages the abundant labeled nodes from a source network to help classify unlabeled nodes in a target network, is studied. The existing domain adaptation algorithms generally fail to model the network structural information, and the current network embedding models mainly focus on single-network applications. Thus, both of them cannot be directly applied to solve the cross-network node classification problem. This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn network-invariant node representations that can also well preserve the network structural information. In ACDNE, the deep network embedding module utilizes two feature extractors to jointly preserve attributed affinity and topological proximities between nodes. In addition, a node classifier is incorporated to make node representations label-discriminative. Moreover, an adversarial domain adaptation technique is employed to make node representations network-invariant. Extensive experimental results demonstrate that the proposed ACDNE model achieves the state-of-the-art performance in cross-network node classification.

Download Full-text

Molecular Graph Contrastive Learning with Parameterized Explainable Augmentations

10.1101/2021.12.03.471150 ◽

2021 ◽

Author(s):

Yingheng Wang ◽

Yaosen Min ◽

Erzhuo Shao ◽

Ji Wu

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Structural Information ◽

Molecular Graph ◽

Representation Learning ◽

Graph Representation ◽

Input Graph ◽

Recent Success ◽

Real World Datasets ◽

Comparative Results

ABSTRACTLearning generalizable, transferable, and robust representations for molecule data has always been a challenge. The recent success of contrastive learning (CL) for self-supervised graph representation learning provides a novel perspective to learn molecule representations. The most prevailing graph CL framework is to maximize the agreement of representations in different augmented graph views. However, existing graph CL frameworks usually adopt stochastic augmentations or schemes according to pre-defined rules on the input graph to obtain different graph views in various scales (e.g. node, edge, and subgraph), which may destroy topological semantemes and domain prior in molecule data, leading to suboptimal performance. Therefore, designing parameterized, learnable, and explainable augmentation is quite necessary for molecular graph contrastive learning. A well-designed parameterized augmentation scheme can preserve chemically meaningful structural information and intrinsically essential attributes for molecule graphs, which helps to learn representations that are insensitive to perturbation on unimportant atoms and bonds. In this paper, we propose a novel Molecular Graph Contrastive Learning with Parameterized Explainable Augmentations, MolCLE for brevity, that self-adaptively incorporates chemically significative information from both topological and semantic aspects of molecular graphs. Specifically, we apply deep neural networks to parameterize the augmentation process for both the molecular graph topology and atom attributes, to highlight contributive molecular substructures and recognize underlying chemical semantemes. Comprehensive experiments on a variety of real-world datasets demonstrate that our proposed method consistently outperforms compared baselines, which verifies the effectiveness of the proposed framework. Detailedly, our self-supervised MolCLE model surpasses many supervised counterparts, and meanwhile only uses hundreds of thousands of parameters to achieve comparative results against the state-of-the-art baseline, which has tens of millions of parameters. We also provide detailed case studies to validate the explainability of augmented graph views.CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Applied computing → Bioinformatics; • Computing methodologies → Neural networks; Unsupervised learning.

Download Full-text

Unsupervised Structural Graph Node Representation Learning

10.18122/td/1754/boisestate ◽

2020 ◽

Author(s):

Mikel Joaristi

Keyword(s):

Real World ◽

State Of The Art ◽

Structural Information ◽

Representation Learning ◽

Graph Representation ◽

Learning Methods ◽

Structural Graph ◽

Connectivity Information ◽

Latent Space ◽

Previous State

Unsupervised Graph Representation Learning methods learn a numerical representation of the nodes in a graph. The generated representations encode meaningful information about the nodes' properties, making them a powerful tool for tasks in many areas of study, such as social sciences, biology or communication networks. These methods are particularly interesting because they facilitate the direct use of standard Machine Learning models on graphs. Graph representation learning methods can be divided into two main categories depending on the information they encode, methods preserving the nodes connectivity information, and methods preserving nodes' structural information. Connectivity-based methods focus on encoding relationships between nodes, with neighboring nodes being closer together in the resulting latent space. On the other hand, structure-based methods generate a latent space where nodes serving a similar structural function in the network are encoded close to each other, independently of them being connected or even close to each other in the graph. While there are a lot of works that focus on preserving nodes' connectivity information, only a few works study the problem of encoding nodes' structure, specially in an unsupervised way. In this dissertation, we demonstrate that properly encoding nodes' structural information is fundamental for many real-world applications, as it can be leveraged to successfully solve many tasks where connectivity-based methods fail. One concrete example is presented first. In this example, the task consists of detecting malicious entities in a real-world financial network. We show that to solve this problem, connectivity information is not enough and show how leveraging structural information provides considerable performance improvements. This particular example pinpoints the need for further research on the area of structural graph representation learning, together with the limitations of the previous state-of-the-art. We use the acquired knowledge as a starting point and inspiration for the research and development of three independent unsupervised structural graph representation learning methods: Structural Iterative Representation learning approach for Graph Nodes (SIR-GN), Structural Iterative Lexicographic Autoencoded Node Representation (SILA), and Sparse Structural Node Representation (SparseStruct). We show how each of our methods tackles specific limitations on the previous state-of-the-art on structural graph representation learning such as scalability, representation meaning, and lack of formal proof that guarantees the preservation of structural properties. We provide an extensive experimental section where we compare our three proposed methods to the current state-of-the-art on both connectivity-based and structure-based representation learning methods. Finally, in this dissertation, we look at extensions of the basic structural graph representation learning problem. We study the problem of temporal structural graph representation. We also provide a method for representation explainability.

Download Full-text

How to Efficiently Determine the Range Precision of 3D Terrestrial Laser Scanners

Sensors ◽

10.3390/s19061466 ◽

2019 ◽

Vol 19 (6) ◽

pp. 1466 ◽

Cited By ~ 14

Author(s):

Berit Schmitz ◽

Christoph Holst ◽

Tomislav Medic ◽

Derek Lichti ◽

Heiner Kuhlmann

Keyword(s):

Laser Scanning ◽

Measurement Accuracy ◽

Intensity Function ◽

Object Surface ◽

Beam Direction ◽

Surface Geometry ◽

Measurement Volume ◽

Laser Scanners ◽

Stochastic Properties

As laser scanning technology has improved a lot in recent years, terrestrial laser scanners (TLS) have become popular devices for surveying tasks with high accuracy demands, such as deformation analyses. For this reason, finding a stochastic model for TLS measurements is very important in order to get statistically reliable results. The measurement accuracy of laser scanners—especially of their rangefinders—is strongly dependent on the scanning conditions, such as the scan configuration, the object surface geometry and the object reflectivity. This study demonstrates a way to determine the intensity-dependent range precision of 3D points for terrestrial laser scanners that measure in 3D mode by using range residuals in laser beam direction of a best plane fit. This method does not require special targets or surfaces aligned perpendicular to the scanner, which allows a much quicker and easier determination of the stochastic properties of the rangefinder. Furthermore, the different intensity types—raw and scaled—intensities are investigated since some manufacturers only provide scaled intensities. It is demonstrated that the intensity function can be derived from raw intensity values as written in literature, and likewise—in a restricted measurement volume—from scaled intensity values if the raw intensities are not available.

Download Full-text

SIR-GN: A Fast Structural Iterative Representation Learning Approach For Graph Nodes

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3450315 ◽

2021 ◽

Vol 15 (6) ◽

pp. 1-39

Author(s):

Mikel Joaristi ◽

Edoardo Serra

Keyword(s):

Structural Information ◽

Representation Learning ◽

Graph Representation ◽

Structural Function ◽

Learning Approach ◽

Numerical Representation ◽

Learning Methods ◽

Computational Performance ◽

Latent Space ◽

Graph Nodes

Graph representation learning methods have attracted an increasing amount of attention in recent years. These methods focus on learning a numerical representation of the nodes in a graph. Learning these representations is a powerful instrument for tasks such as graph mining, visualization, and hashing. They are of particular interest because they facilitate the direct use of standard machine learning models on graphs. Graph representation learning methods can be divided into two main categories: methods preserving the connectivity information of the nodes and methods preserving nodes’ structural information. Connectivity-based methods focus on encoding relationships between nodes, with connected nodes being closer together in the resulting latent space. While methods preserving structure generate a latent space where nodes serving a similar structural function in the network are encoded close to each other, independently of them being connected or even close to each other in the graph. While there are a lot of works that focus on preserving node connectivity, only a few works focus on preserving nodes’ structure. Properly encoding nodes’ structural information is fundamental for many real-world applications as it has been demonstrated that this information can be leveraged to successfully solve many tasks where connectivity-based methods usually fail. A typical example is the task of node classification, i.e., the assignment or prediction of a particular label for a node. Current limitations of structural representation methods are their scalability, representation meaning, and no formal proof that guaranteed the preservation of structural properties. We propose a new graph representation learning method, called Structural Iterative Representation learning approach for Graph Nodes ( SIR-GN ). In this work, we propose two variations ( SIR-GN: GMM and SIR-GN: K-Means ) and show how our best variation SIR-GN: K-Means : (1) theoretically guarantees the preservation of graph structural similarities, (2) provides a clear meaning about its representation and a way to interpret it with a specifically designed attribution procedure, and (3) is scalable and fast to compute. In addition, from our experiment, we show that SIR-GN: K-Means is often better or, in the worst-case comparable than the existing structural graph representation learning methods present in the literature. Also, we empirically show its superior scalability and computational performance when compared to other existing approaches.

Download Full-text