Distributed Kronecker Graph Generation with Ground Truth of Many Graph Properties

Author(s):  
Trevor Steil ◽  
Benjamin Priest ◽  
Geoffrey Sanders ◽  
Roger Pearce ◽  
Timothy La Fond ◽  
...  
2020 ◽  
Vol 34 (07) ◽  
pp. 11237-11245
Author(s):  
Mahmoud Khademi ◽  
Oliver Schulte

We propose a new algorithm, called Deep Generative Probabilistic Graph Neural Networks (DG-PGNN), to generate a scene graph for an image. The input to DG-PGNN is an image, together with a set of region-grounded captions and object bounding-box proposals for the image. To generate the scene graph, DG-PGNN constructs and updates a new model, called a Probabilistic Graph Network (PGN). A PGN can be thought of as a scene graph with uncertainty: it represents each node and each edge by a CNN feature vector and defines a probability mass function (PMF) for node-type (object category) of each node and edge-type (predicate class) of each edge. The DG-PGNN sequentially adds a new node to the current PGN by learning the optimal ordering in a Deep Q-learning framework, where states are partial PGNs, actions choose a new node, and rewards are defined based on the ground-truth. After adding a node, DG-PGNN uses message passing to update the feature vectors of the current PGN by leveraging contextual relationship information, object co-occurrences, and language priors from captions. The updated features are then used to fine-tune the PMFs. Our experiments show that the proposed algorithm significantly outperforms the state-of-the-art results on the Visual Genome dataset for scene graph generation. We also show that the scene graphs constructed by DG-PGNN improve performance on the visual question answering task, for questions that need reasoning about objects and their interactions in the scene context.


Methodology ◽  
2019 ◽  
Vol 15 (Supplement 1) ◽  
pp. 43-60 ◽  
Author(s):  
Florian Scharf ◽  
Steffen Nestler

Abstract. It is challenging to apply exploratory factor analysis (EFA) to event-related potential (ERP) data because such data are characterized by substantial temporal overlap (i.e., large cross-loadings) between the factors, and, because researchers are typically interested in the results of subsequent analyses (e.g., experimental condition effects on the level of the factor scores). In this context, relatively small deviations in the estimated factor solution from the unknown ground truth may result in substantially biased estimates of condition effects (rotation bias). Thus, in order to apply EFA to ERP data researchers need rotation methods that are able to both recover perfect simple structure where it exists and to tolerate substantial cross-loadings between the factors where appropriate. We had two aims in the present paper. First, to extend previous research, we wanted to better understand the behavior of the rotation bias for typical ERP data. To this end, we compared the performance of a variety of factor rotation methods under conditions of varying amounts of temporal overlap between the factors. Second, we wanted to investigate whether the recently proposed component loss rotation is better able to decrease the bias than traditional simple structure rotation. The results showed that no single rotation method was generally superior across all conditions. Component loss rotation showed the best all-round performance across the investigated conditions. We conclude that Component loss rotation is a suitable alternative to simple structure rotation. We discuss this result in the light of recently proposed sparse factor analysis approaches.


2020 ◽  
Vol 77 (4) ◽  
pp. 1609-1622
Author(s):  
Franziska Mathies ◽  
Catharina Lange ◽  
Anja Mäurer ◽  
Ivayla Apostolova ◽  
Susanne Klutmann ◽  
...  

Background: Positron emission tomography (PET) of the brain with 2-[F-18]-fluoro-2-deoxy-D-glucose (FDG) is widely used for the etiological diagnosis of clinically uncertain cognitive impairment (CUCI). Acute full-blown delirium can cause reversible alterations of FDG uptake that mimic neurodegenerative disease. Objective: This study tested whether delirium in remission affects the performance of FDG PET for differentiation between neurodegenerative and non-neurodegenerative etiology of CUCI. Methods: The study included 88 patients (82.0±5.7 y) with newly detected CUCI during hospitalization in a geriatric unit. Twenty-seven (31%) of the patients were diagnosed with delirium during their current hospital stay, which, however, at time of enrollment was in remission so that delirium was not considered the primary cause of the CUCI. Cases were categorized as neurodegenerative or non-neurodegenerative etiology based on visual inspection of FDG PET. The diagnosis at clinical follow-up after ≥12 months served as ground truth to evaluate the diagnostic performance of FDG PET. Results: FDG PET was categorized as neurodegenerative in 51 (58%) of the patients. Follow-up after 16±3 months was obtained in 68 (77%) of the patients. The clinical follow-up diagnosis confirmed the FDG PET-based categorization in 60 patients (88%, 4 false negative and 4 false positive cases with respect to detection of neurodegeneration). The fraction of correct PET-based categorization did not differ between patients with delirium in remission and patients without delirium (86% versus 89%, p = 0.666). Conclusion: Brain FDG PET is useful for the etiological diagnosis of CUCI in hospitalized geriatric patients, as well as in patients with delirium in remission.


2020 ◽  
Vol 64 (5) ◽  
pp. 50411-1-50411-8
Author(s):  
Hoda Aghaei ◽  
Brian Funt

Abstract For research in the field of illumination estimation and color constancy, there is a need for ground-truth measurement of the illumination color at many locations within multi-illuminant scenes. A practical approach to obtaining such ground-truth illumination data is presented here. The proposed method involves using a drone to carry a gray ball of known percent surface spectral reflectance throughout a scene while photographing it frequently during the flight using a calibrated camera. The captured images are then post-processed. In the post-processing step, machine vision techniques are used to detect the gray ball within each frame. The camera RGB of light reflected from the gray ball provides a measure of the illumination color at that location. In total, the dataset contains 30 scenes with 100 illumination measurements on average per scene. The dataset is available for download free of charge.


Author(s):  
Yanli Feng ◽  
Gongliang Sun ◽  
Zhiyao Liu ◽  
Chenrui Wu ◽  
Xiaoyang Zhu ◽  
...  

2020 ◽  
Author(s):  
Jingbai Li ◽  
Patrick Reiser ◽  
André Eberhard ◽  
Pascal Friederich ◽  
Steven Lopez

<p>Photochemical reactions are being increasingly used to construct complex molecular architectures with mild and straightforward reaction conditions. Computational techniques are increasingly important to understand the reactivities and chemoselectivities of photochemical isomerization reactions because they offer molecular bonding information along the excited-state(s) of photodynamics. These photodynamics simulations are resource-intensive and are typically limited to 1–10 picoseconds and 1,000 trajectories due to high computational cost. Most organic photochemical reactions have excited-state lifetimes exceeding 1 picosecond, which places them outside possible computational studies. Westermeyr <i>et al.</i> demonstrated that a machine learning approach could significantly lengthen photodynamics simulation times for a model system, methylenimmonium cation (CH<sub>2</sub>NH<sub>2</sub><sup>+</sup>).</p><p>We have developed a Python-based code, Python Rapid Artificial Intelligence <i>Ab Initio</i> Molecular Dynamics (PyRAI<sup>2</sup>MD), to accomplish the unprecedented 10 ns <i>cis-trans</i> photodynamics of <i>trans</i>-hexafluoro-2-butene (CF<sub>3</sub>–CH=CH–CF<sub>3</sub>) in 3.5 days. The same simulation would take approximately 58 years with ground-truth multiconfigurational dynamics. We proposed an innovative scheme combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to effectively sample the initial data, facilitating the adaptive sampling to generate an informative and data-efficient training set with 6,232 data points. Our neural networks achieved chemical accuracy (mean absolute error of 0.032 eV). Our 4,814 trajectories reproduced the S<sub>1</sub> half-life (60.5 fs), the photochemical product ratio (<i>trans</i>: <i>cis</i> = 2.3: 1), and autonomously discovered a pathway towards a carbene. The neural networks have also shown the capability of generalizing the full potential energy surface with chemically incomplete data (<i>trans</i> → <i>cis</i> but not <i>cis</i> → <i>trans</i> pathways) that may offer future automated photochemical reaction discoveries.</p>


Author(s):  
A. V. Ponomarev

Introduction: Large-scale human-computer systems involving people of various skills and motivation into the information processing process are currently used in a wide spectrum of applications. An acute problem in such systems is assessing the expected quality of each contributor; for example, in order to penalize incompetent or inaccurate ones and to promote diligent ones.Purpose: To develop a method of assessing the expected contributor’s quality in community tagging systems. This method should only use generally unreliable and incomplete information provided by contributors (with ground truth tags unknown).Results:A mathematical model is proposed for community image tagging (including the model of a contributor), along with a method of assessing the expected contributor’s quality. The method is based on comparing tag sets provided by different contributors for the same images, being a modification of pairwise comparison method with preference relation replaced by a special domination characteristic. Expected contributors’ quality is evaluated as a positive eigenvector of a pairwise domination characteristic matrix. Community tagging simulation has confirmed that the proposed method allows you to adequately estimate the expected quality of community tagging system contributors (provided that the contributors' behavior fits the proposed model).Practical relevance: The obtained results can be used in the development of systems based on coordinated efforts of community (primarily, community tagging systems). 


1999 ◽  
Author(s):  
Jr Austin ◽  
Fulthorpe James A. ◽  
Olson Craig S. ◽  
Hilary

Sign in / Sign up

Export Citation Format

Share Document