Graph Template Research Articles

Iterative active learning strategies for subgraph matching

The subgraph matching problem arises in a variety of domains including pattern recognition for segmented images, meshes of 3D objects, biochemical reactions, and security applications. Large and complex solution spaces are common for this graph-based problem, especially when the world graph contains many more nodes and edges in comparison to the template graph. Researchers have focused on the task of finding one match or many matches, however a real use-case scenario can necessitate identifying specific matches from a combinatorially complex solution space. Our work directly addresses this challenge. We propose to introduce additional queries to the subgraph that iteratively reduce the size of the solution space, and consider the optimal strategy for doing so. We formalize this problem and demonstrate that it is NP-complete. We compare different quantitative criteria for choosing nodes to query. We introduce a new method based on a spanning tree that outperforms other graph-based criteria for the multichannel datasets. Finally, we present numerical experiments for single channel and multichannel subgraph matching problems created from both synthetic and real world datasets.

Remote-Sensing Image Scene Classification via Graph Template Enhancement and Supplementation Network with Dual-Teacher Knowledge Distillation

Remote-Sensing Image Scene Classification via Graph Template Enhancement and Supplementation Network with Dual-Teacher Knowledge Distillation

Estimating the connectional brain template based on multi-view networks with bi-channel graph neural network

Multi-view networks constructed from multiple brain functional or structural measures (e.g., fractional anisotropy, fiber number, and fiber length, etc.) describe brain connectivity from different views. The connectional brain template (CBT) of multi-view networks from a given population provides a standard graph template incorporating complementary information for analyzing intergroup differences. However, preserving the complex topology of multi-view networks and building the CBT end-to-end remains challenging. Hence, we proposed a bi-channel convolution framework, including a local connection channel (LCC) with edge-conditioned convolution layers and a global network channel (GNC) with graph convolution network, to estimate the CBT in an end-to-end manner. The LCC captured the local connection topology across individual networks, and the GNC learned the global network topology through the high-order population network built by the similarity between the node strength distributions of individual networks for each view. Additionally, we improved topological similarity constraint in the loss function by minimizing the KL divergence of the node strength and degree distributions between the CBT and multi-view networks. Compared with four existing methods, our CBT exhibited optimal centrality, topological structure retention ability and differentiation between the younger and older age groups. Using the harmonic bases of the CBT, we found that the total harmonic energy of cortical thickness presented significant differences among different age groups. Our method provided a standard common template for examining the structural connection changes in the spatial domain and the anatomical features alterations in the harmonic domain, thus distinguishing the different population groups.

Cross-Correlation Fusion Graph Convolution-Based Object Tracking

Most popular graph attention networks treat pixels of a feature map as individual nodes, which makes the feature embedding extracted by the graph convolution lack the integrity of the object. Moreover, matching between a template graph and a search graph using only part-level information usually causes tracking errors, especially in occlusion and similarity situations. To address these problems, we propose a novel end-to-end graph attention tracking framework that has high symmetry, combining traditional cross-correlation operations directly. By utilizing cross-correlation operations, we effectively compensate for the dispersion of graph nodes and enhance the representation of features. Additionally, our graph attention fusion model performs both part-to-part matching and global matching, allowing for more accurate information embedding in the template and search regions. Furthermore, we optimize the information embedding between the template and search branches to achieve better single-object tracking results, particularly in occlusion and similarity scenarios. The flexibility of graph nodes and the comprehensiveness of information embedding have brought significant performance improvements in our framework. Extensive experiments on three challenging public datasets (LaSOT, GOT-10k, and VOT2016) show that our tracker outperforms other state-of-the-art trackers.

Graph-based Automated Macro-Molecule Assembly.

We present a general molecular framework assembly algorithm that takes a largely arbitrary molecular fragment database and a user-supplied target template graph as input. Automatic assembly of molecular fragments from the database, following a prescribed, user-supplied set of connection rules, then turns the template graph into an actual, chemically reasonable molecular framework. Assembly capabilities of our algorithm are tested by producing several abstract, closed-loop shapes. To indicate a few of many possible application areas we demonstrate a host-guest complex and a road toward catalysis. Postassembly substituent exchange can be used to produce electric fields of desired values at desired points inside the framework or at its surface as a stepping stone toward rationally designed, artificial heterogeneous catalysts.

Multigraph classification using learnable integration network with application to gender fingerprinting

Multigraphs with heterogeneous views present one of the most challenging obstacles to classification tasks due to their complexity. Several works based on feature selection have been recently proposed to disentangle the problem of multigraph heterogeneity. However, such techniques have major drawbacks. First, the bulk of such works lies in the vectorization and the flattening operations, failing to preserve and exploit the rich topological properties of the multigraph. Second, they learn the classification process in a dichotomized manner where the cascaded learning steps are pieced in together independently. Hence, such architectures are inherently agnostic to the cumulative estimation error from step to step. To overcome these drawbacks, we introduce MICNet (multigraph integration and classifier network), the first end-to-end graph neural network based model for multigraph classification. First, we learn a single-view graph representation of a heterogeneous multigraph using a GNN based integration model. The integration process in our model helps tease apart the heterogeneity across the different views of the multigraph by generating a subject-specific graph template while preserving its geometrical and topological properties conserving the node-wise information while reducing the size of the graph (i.e., number of views). Second, we classify each integrated template using a geometric deep learning block which enables us to grasp the salient graph features. We train, in end-to-end fashion, these two blocks using a single objective function to optimize the classification performance. We evaluate our MICNet in gender classification using brain multigraphs derived from different cortical measures. We demonstrate that our MICNet significantly outperformed its variants thereby showing its great potential in multigraph classification.

Identification of Autism Spectrum Disorder With Functional Graph Discriminative Network.

Autism spectrum disorder (ASD) is a specific brain disease that causes communication impairments and restricted interests. Functional connectivity analysis methodology is widely used in neuroscience research and shows much potential in discriminating ASD patients from healthy controls. However, due to heterogeneity of ASD patients, the performance of conventional functional connectivity classification methods is relatively poor. Graph neural network is an effective graph representation method to model structured data like functional connectivity. In this paper, we proposed a functional graph discriminative network (FGDN) for ASD classification. On the basis of pre-built graph templates, the proposed FGDN is able to effectively distinguish ASD patient from health controls. Moreover, we studied the size of training set for effective training, inter-site predictions, and discriminative brain regions. Discriminative brain regions were determined by the proposed model to investigate its applicability and biomarkers for ASD identification. For functional connectivity classification and analysis, FGDN is not only an effective tool for ASD identification but also a potential technique in neuroscience research.

My Cancer Genome: Coevolution of Precision Oncology and a Molecular Oncology Knowledgebase.

PURPOSEThe My Cancer Genome (MCG) knowledgebase and resulting website were launched in 2011 with the purpose of guiding clinicians in the application of genomic testing results for treatment of patients with cancer. Both knowledgebase and website were originally developed using a wiki-style approach that relied on manual evidence curation and synthesis of that evidence into cancer-related biomarker, disease, and pathway pages on the website that summarized the literature for a clinical audience. This approach required significant time investment for each page, which limited website scalability as the field advanced. To address this challenge, we designed and used an assertion-based data model that allows the knowledgebase and website to expand with the field of precision oncology.METHODSAssertions, or computationally accessible cause and effect statements, are both manually curated from primary sources and imported from external databases and stored in a knowledge management system. To generate pages for the MCG website, reusable templates transform assertions into reconfigurable text and visualizations that form the building blocks for automatically updating disease, biomarker, drug, and clinical trial pages.RESULTSCombining text and graph templates with assertions in our knowledgebase allows generation of web pages that automatically update with our knowledgebase. Automated page generation empowers rapid scaling of the website as assertions with new biomarkers and drugs are added to the knowledgebase. This process has generated more than 9,100 clinical trial pages, 18,100 gene and alteration pages, 900 disease pages, and 2,700 drug pages to date.CONCLUSIONLeveraging both computational and manual curation processes in combination with reusable templates empowers automation and scalability for both the MCG knowledgebase and MCG website.

Subgraph Matching on Multiplex Networks

An active area of research in computational science is the design of algorithms for solving the subgraph matching problem to find copies of a given template graph in a larger world graph. Prior works have largely addressed single-channel networks using a variety of approaches. We present a suite of filtering methods for subgraph isomorphisms for multiplex networks (with different types of edges between nodes and more than one edge within each channel type). We aim to understand the entire solution space rather than focusing on finding one isomorphism. Results are shown on several classes of datasets: (a) Sudoku puzzles mapped to the subgraph isomorphism problem, (b) Erdös-Rényi multigraphs, (c) real-world datasets from Twitter and transportation networks, (d) synthetic data created for the DARPA MAA program.

A diagnostic unified classification model for classifying multi-sized and multi-modal brain graphs using graph alignment

BackgroundPresence of multimodal brain graphs derived from different neuroimaging modalities is inarguably one of the most critical challenges in building unified classification models that can be trained and tested on any brain graph regardless of its size and the modality it was derived from. Existing methodsOne solution is to learn a model for each modality independently, which is cumbersome and becomes more time-consuming as the number of modalities increases. Another traditional solution is to build a model inputting multimodal brain graphs for the target prediction task; however, this is only applicable to datasets where all samples have joint neuro-modalities. New methodIn this paper, we propose to build a unified brain graph classification model trained on unpaired multimodal brain graphs, which can classify any brain graph of any size. This is enabled by incorporating a graph alignment step where all multi-modal graphs of different sizes and heterogeneous distributions are mapped to a common template graph. Next, we design a graph alignment strategy to the target fixed-size template and further apply linear discriminant analysis (LDA) to the aligned graphs as a supervised dimensionality reduction technique for the target classification task. ResultsWe tested our method on unpaired autistic and healthy brain connectomes derived from functional and morphological MRI datasets (two modalities). ConclusionOur results showed that our unified model method not only has great promise in solving such a challenging problem but achieves comparable performance to models trained on each modality independently.

Using Named Graphs and Knowledge Graph Template Patterns for Efficiently Organizing FAIR Anatomy Data and Metadata

Currently, morphological data and metadata are still mostly published as unstructured free texts, which lack semantic transparency, cannot be parsed by computers, and do not comply with the FAIR (Findable, Accessible, Interoperable, Reusable; Wilkinson et al. (2016) data principles, thus hampering their reuse by non-experts and their integration across many fields in the life sciences. With an ever-increasing amount of available ontologies and the development of adequate semantic technology, however, a solution to this problem becomes available. Instead of free text descriptions, morphological data and metadata can be recorded, stored, and communicated through the Web in the form of Resource Description Framework (RDF) triple statements that use the ‘Subject – Property – Object’ syntax of RDF and URIs of ontology classes and properties as well as URIs for individual entities as terminology. Since a given URI can take the ‘Subject’ position in one and the ‘Object’ position in another RDF statement, several triples can be linked to form a highly formalized and structured directed graph (semantic graph). After introducing an instance-based approach of recording morphological descriptions and their accompanying metadata as semantic knowledge graphs (i.e. Anatomy Knowledge Graphs), we propose a knowledge graph template pattern for each type of anatomical observation and a pattern for documenting metadata. The use of template patterns for knowledge graphs provides Interoperability and Reusability of comparable anatomical observations and of their accompanying metadata and a means to meaningfully visualize information contained in semantic graphs in a user-friendly HTML representation. Stored in a tuple store, Anatomy Knowledge Graphs become Findable and Accessible through the store’s SPARQL endpoint. As a consequence, anatomy data and metadata documented as Anatomy Knowledge Graphs in a tuple store are FAIR. Finally, we suggest a general scheme of how to efficiently organize Anatomy Knowledge Graphs in a tuple store framework based on instances of named graphs, with each individual named graph instantiating an ontology class that relates to a particular type of observation (e.g., weight measurement named graph class). A named graph is a fourth element in an RDF statement (‘Subject – Property – Object – Named Graph’), turning the triple into a quadruple. All RDF statements that share the same URI in the ‘Named Graph’ position belong to the same named graph. The use of named graph resources allows meaningful fragmentation of the contents of an Anatomy Knowledge Graph (Fig. 1), which in turn enables subsequent specification of all kinds of data views for managing and accessing morphological data and metadata. This scheme has been implemented in the description module of the prototype for semantic Morph∙D∙Base.

AIDIS: Detecting and classifying anomalous behavior in ubiquitous kernel processes

Targeted attacks on IT systems are a rising threat against the confidentiality, integrity, and availability of critical information and infrastructures. With the rising prominence of advanced persistent threats (APTs), identifying and understanding such attacks has become increasingly important. Current signature-based systems are heavily reliant on fixed patterns that struggle with unknown or evasive applications, while behavior-based solutions usually leave most of the interpretative work to a human analyst.In this article we propose AIDIS, an Advanced Intrusion Detection and Interpretation System capable to explain anomalous behavior within a network-enabled user session by considering kernel event anomalies identified through their deviation from a set of baseline process graphs. For this purpose we adapt star structures, a bipartite representation used to approximate the edit distance between two graphs. Baseline templates are generated automatically and adapt to the nature of the respective operating system process.We prototypically implemented smart anomaly classification through a set of competency questions applied to graph template deviations and evaluated the approach using both Random Forest and linear kernel support vector machines. The determined attack classes are ultimately mapped to a dedicated APT attacker/defender meta model that considers actions, actors, as well as assets and mitigating controls, thereby enabling decision support and contextual interpretation of ongoing attacks.

A 3D Human Body and Face Fitting System Based on Deformation Graph and Mesh Template

A 3D Human Body and Face Fitting System Based on Deformation Graph and Mesh Template

Modeling of Generic Offshore Vessel in Crane Operations With Focus on Strong Rigid Body Connections

Both marine surface vehicles and underwater vehicles are often equipped with cranes, robotic manipulators, or similar equipment. Much attention is given to modeling of both the dynamics of marine vehicles and the dynamics of manipulators, cranes, and other equipment. However, less attention is given to the interconnected behavior of the vehicle and equipment, even though such equipment may have a considerable impact on the vehicle dynamic behavior, and therefore risk, or conversely, the vehicle may have a considerable impact on the equipment dynamic behavior. With main focus on ships equipped with cranes, this paper presents a framework for modeling the interconnected dynamics of rigid body systems, based on Lagrangian dynamics. The resulting equations of motion are implemented as a bond graph template to which any subsystem of interest, such as actuators, hydrodynamics, and controllers, may be interfaced. An example on how this framework can be used to develop a high-fidelity simulator of an offshore installation vessel with a heavy duty crane is presented. This work represents the first bond graph implementation of crane and vessel dynamics where the interconnections are modeled according to true physical rigid body principles without nonphysical limitations such as diagonal mass-inertia matrix.

Querying of Disparate Association and Interaction Data in Biomedical Applications.

In biomedical applications, network models are commonly used to represent interactions and higher-level associations among biological entities. Integrated analyses of these interaction and association data has proven useful in extracting knowledge, and generating novel hypotheses for biomedical research. However, since most datasets provide their own schema and query interface, opportunities for exploratory and integrative querying of disparate data are currently limited. In this study, we utilize RDF-based representations of biomedical interaction and association data to develop a querying framework that enables flexible specification and efficient processing of graph template matching queries. The proposed framework enables integrative querying of biomedical databases to discover complex patterns of associations among a diverse range of biological entities, including biomolecules, biological processes, organisms, and phenotypes. Our experimental results on the UniProt dataset show that the proposed framework can be used to efficiently process complex queries, and identify biologically relevant patterns of associations that cannot be readily obtained by querying each dataset independently.

Tangible 3D modeling of coherent and themed structures

We present CubeBuilder, a system for interactive, tangible 3D shape modeling. CubeBuilder allows the user to create a digital 3D model by placing physical, non-interlocking cubic blocks. These blocks may be placed in a completely arbitrary fashion and combined with other objects. In effect, this turns the task of 3D modeling into a playful activity that hardly requires any learning on the part of the user. The blocks are registered using a depth camera and entered into the cube graph where each block is a node and adjacent blocks are connected by edges. From the cube graph, we transform the initial cubes into coherent structures by generating smooth connection geometry for some edges of the graph. Based on an analysis of the cube graph, we identify subgraphs that match given graph templates. These subgraph templates map to predefined geometric refinements of the basic shape. This, in turn, allows the user to tangibly build structures of greater details than the blocks provide in and of themselves. We show a number of shapes that have been modeled by users and are indicative of the expressive power of the system. Furthermore, we demonstrate the scalability of the tangible interface which appears to be limited only by the number of blocks available.

Object Discovery: Soft Attributed Graph Mining.

We categorize this research in terms of its contribution to both graph theory and computer vision. From the theoretical perspective, this study can be considered as the first attempt to formulate the idea of mining maximal frequent subgraphs in the challenging domain of messy visual data, and as a conceptual extension to the unsupervised learning of graph matching. We define a soft attributed pattern (SAP) to represent the common subgraph pattern among a set of attributed relational graphs (ARGs), considering both their structure and attributes. Regarding the differences between ARGs with fuzzy attributes and conventional labeled graphs, we propose a new mining strategy that directly extracts the SAP with the maximal graph size without applying node enumeration. Given an initial graph template and a number of ARGs, we develop an unsupervised method to modify the graph template into the maximal-size SAP. From a practical perspective, this research develops a general platform for learning the category model (i.e., the SAP) from cluttered visual data (i.e., the ARGs) without labeling "what is where," thereby opening the possibility for a series of applications in the era of big visual data. Experiments demonstrate the superior performance of the proposed method on RGB/RGB-D images and videos.

Cluttered indoor scene modeling via functional part-guided graph matching

We propose an automatic method for fast reconstruction of indoor scenes from raw point scans, which is a fairly challenging problem due to the restricted accessibility and the cluttered space for indoor environment. We first detect and remove points representing the ground, walls and ceiling from the input data and cluster the remaining points into different groups, referred to as sub-scenes. Our approach abstracts the sub-scenes with geometric primitives, and accordingly constructs the topology graphs with structural attributes based on the functional parts of objects (namely, anchors). To decompose sub-scenes into individual indoor objects, we devise an anchor-guided subgraph matching algorithm which leverages template graphs to partition the graphs into subgraphs (i.e., individual objects), which is capable of handling arbitrarily oriented objects within scenes. Subsequently, we present a data-driven approach to model individual objects, which is particularly formulated as a model instance recognition problem. A Randomized Decision Forest (RDF) is introduced to achieve robust recognition on decomposed indoor objects with raw point data. We further exploit template fitting to generate the geometrically faithful model to the input indoor scene. We visually and quantitatively evaluate the performance of our framework on a variety of synthetic and raw scans, which comprehensively demonstrates the efficiency and robustness of our reconstruction method on raw scanned point clouds, even in the presence of noise and heavy occlusions.

Automatic belief network modeling via policy inference for SDN fault localization

Fault localization for SDN becomes one of the most critical but difficult tasks. Existing tools typically only address a specific part of the problem (e.g., control plane verification, flow checker). In this paper, we propose a new approach to tackle SDN fault localization by automatically Modeling via Policy Inference (called MPI) the causality between SDN faults and their symptoms to a belief network. In the MPI system, a service oriented high level policy language is used to specify network services provisioned between end nodes. MPI parses each service provisioning policy to a logical policy view, which consists of a pair of logical end nodes, a traffic pattern specification, and a list of required network functions (or a service function chain). An SDN controller takes the policies from multiple parties and provisions the requested services on its orchestrated SDN network. MPI queries the controller about the network topology and retrieves flow rules from all SDN switches. MPI maps the policy view to the corresponding implementation view, in which all the logical components in the policy view are mapped to the actual system components along with the actual network topology. Referring to the component causality graph templates derived from SDN reference model, the implementation view of the current running network services can be modeled as a belief network. A heuristic fault reasoning algorithm is adopted to search for the most likely root causes. MPI has been evaluated in both a simulation environment and a real network system for its accuracy and efficiency. The evaluation shows that MPI is a highly scalable, effective and flexible modeling approach to tackle fault localization challenges in a highly dynamic and agile SDN network.

A novel technique of custom ocular prosthesis fabrication

The literature provides several techniques for fabricating ocular prostheses, ranging from stock to custom-made prostheses. A cosmetically acceptable ocular prosthesis is that which reproduces the colour, form and orientation of the iris and allows the patient to return to a ifestyle to which they were previously accustomed. A sequence of steps for construction of custom-made ocular prostheses is outlined in this case report with emphasis on accurate positioning of iris using a transparent graph template. Ocular rehabilitation restores the compromised aesthetics, maintains the normal physiology of the ocular area, and increases the social life and self-esteem of the patient.