1,720,979 research outputs found
Graph Neural Networks with Parallel Local Neighborhood Aggregations
No full textGraph neural networks (GNNs) have become very popular for processing and analyzing graph-structured data in the last few years. Using message passing as their basic building blocks that aggregate information from neighborhoods, GNN architectures learn low-dimensional graph-level or node-level embeddings useful for several downstream machine learning tasks. In this thesis, we focus on GNN architectures that perform parallel neighborhood aggregations (in short, referred to as PA-GNNs) for two tasks, namely, graph classification and link prediction. Such architectures have a natural advantage of reduced training and inference time as neighborhood aggregation is done before training, unlike GNNs that perform the neighborhood aggregation sequentially (referred to as SA-GNNs) during training. Thus, the runtime of SA-GNNs depends on the number of edges in the graph.
In the first part of the thesis, we propose a generic model for GNNs with parallel neighborhood aggregation and theoretically characterize the discriminative power of PA-GNN models to discriminate between two non-isomorphic graphs. We provide conditions under which they are provably powerful as the well-known Weisfeiler-Lehman graph isomorphism test. We then specialize the generic PA-GNN model and propose a GNN architecture, which we call SPIN: simple and parallel graph isomorphism network. Next to the theoretical characterization of the developed PA-GNN model, we also present numerical experiments on a diverse variety of real-world benchmark graph classification datasets related to social networks, chemical molecular data, and brain networks. The proposed model achieves state-of-the-art performance with reduced training and inference time.
In the second part of the thesis, we propose a computational method for drug repurposing by presenting a deep learning model that captures the complex interactions between the drugs, diseases, genes, and anatomies in a large-scale interactome with over 1.4 million connections. Specifically, we propose a PA-GNN based drug repurposing architecture, which we call GDRnet, to screen a large drug database of clinically approved drugs and predict potential drugs that can be repurposed for novel diseases. GNN-based machine learning models are a natural choice for computational drug repurposing because of their ability to capture the underlying structural information in such complex biological networks. While the proposed PA-GNN architecture is computationally attractive, we present results from numerical experiments to show the efficacy of GNNs for drug repurposing. We also provide numerical experimental results on drug repurposing for coronavirus diseases (including COVID-19), where many of the drugs predicted by the proposed model are considered as the mainstay treatment
Self-Calibration of Acoustic Scalar and Vector Sensor Arrays
No full textIn this work, we consider the self-calibration problem of joint calibration and direction-of-Arrival (DOA) estimation using acoustic sensor arrays. Unlike many previous iterative approaches, we propose solvers that can be readily used for both linear and non-linear arrays for jointly estimating the sensor gain, phase errors, and the source DOAs. We derive these algorithms for both the conventional element-space and covariance data models. We focus on sparse and regular arrays formed using scalar sensors as well as vector sensors. The developed algorithms are obtained by transforming the underlying non-linear calibration model into a linear model, and subsequently by using convex relaxation techniques to estimate the unknown parameters. We also derive identifiability conditions for the existence of a unique solution to the self-calibration problem. To demonstrate the effectiveness of the developed techniques, numerical experiments, and comparisons to the state-of-The-Art methods are provided. Finally, the results from an experiment that was performed in an anechoic chamber using an acoustic vector sensor array are presented to demonstrate the usefulness of the proposed self-calibration techniques.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Signal Processing System
Multidomain Graph Signal Processing: Learning and Sampling
No full textIn this era of data deluge, we are overwhelmed with massive volumes of extremely complex datasets. Data generated today is complex because it lacks a clear geometric structure, comes in great volumes, and it often contains information from multiple domains. In this thesis, we address these issues and propose two theoretical frameworks to handle such multidomain dataset.To begin with, we extend the recently developed geometric deep learning framework to multidomain graph signals, e.g., time-varying signals, defining a new type of convolutional layer that will allow us to deal with graph signals defined on top of several domains, e.g., electroencephalograms or traffic networks. After discussing its properties and motivating its use, we show how this operation can be efficiently implemented to run on a GPU and demonstrate its generalization abilities on a synthetic dataset.Next, we consider the problem of designing sparse sampling strategies for multidomain signals, which can be represented using tensors. To keep the framework general, we do not restrict ourselves to multidomain signals defined on irregular domains. Nonetheless, this particularization to multidomain graph signals is also presented. To do so, we leverage the multidomain structure of tensor signals and propose to acquire samples using a Kronecker-structured sensing function, thereby circumventing the curse of dimensionality. For designing such sensing functions, we develop several low-complexity greedy algorithms based on submodular optimization methods that compute near-optimal sampling sets. To validate the developed theory, we present several numerical examples, ranging from multi-antenna communications to graph signal processing
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
Subsampling for graph power spectrum estimation
No full textIn this paper we focus on subsampling stationary random signals that reside on the vertices of undirected graphs. Second-order stationary graph signals are obtained by filtering white noise and they admit a well-defined power spectrum. Estimating the graph power spectrum forms a central component of stationary graph signal processing and related inference tasks. We show that by sampling a significantly smaller subset of vertices and using simple least squares, we can reconstruct the power spectrum of the graph signal from the subsampled observations, without any spectral priors. In addition, a near-optimal greedy algorithm is developed to design the subsampling scheme.This work was supported by the KAUST-MIT-TUD consortium grant OSR-2015-Sensors-2700
- …
