Search

Overlapping community detection is a key problem in graph mining. Some research has considered applying graph convolutional networks (GCN) to tackle the problem. However, it is still challenging to incorporate deep graph convolutional networks in the case of general irregular graphs. In this study, we design a deep dynamic residual graph convolutional network (DynaResGCN) based on our novel dynamic dilated aggregation mechanisms and a unified end-to-end encoder-decoder-based framework to detect overlapping communities in networks. The deep DynaResGCN model is used as the encoder, whereas we incorporate the Bernoulli-Poisson (BP) model as the decoder. Consequently, we apply our overlapping community detection framework in a research topics dataset without having ground truth, a set of networks from Facebook having a reliable (hand-labeled) ground truth, and in a set of very large co-authorship networks having empirical (not hand-labeled) ground truth. Our experimentation on these datasets shows significantly superior performance over many state-of-the-art methods for the detection of overlapping communities in networks., Comment: Will resubmit later

Objective: Computer-aided disease diagnosis and prognosis based on medical images is a rapidly emerging field. Many Convolutional Neural Network (CNN) architectures have been developed by researchers for disease classification and localization from chest X-ray images. It is known that different thoracic disease lesions are more likely to occur in specific anatomical regions compared to others. This article aims to incorporate this disease and region-dependent prior probability distribution within a deep learning framework. Methods: We present the ThoraX-PriorNet, a novel attention-based CNN model for thoracic disease classification. We first estimate a disease-dependent spatial probability, i.e., an anatomical prior, that indicates the probability of occurrence of a disease in a specific region in a chest X-ray image. Next, we develop a novel attention-based classification model that combines information from the estimated anatomical prior and automatically extracted chest region of interest (ROI) masks to provide attention to the feature maps generated from a deep convolution network. Unlike previous works that utilize various self-attention mechanisms, the proposed method leverages the extracted chest ROI masks along with the probabilistic anatomical prior information, which selects the region of interest for different diseases to provide attention. Results: The proposed method shows superior performance in disease classification on the NIH ChestX-ray14 dataset compared to existing state-of-the-art methods while reaching an area under the ROC curve (%AUC) of 84.67. Regarding disease localization, the anatomy prior attention method shows competitive performance compared to state-of-the-art methods, achieving an accuracy of 0.80, 0.63, 0.49, 0.33, 0.28, 0.21, and 0.04 with an Intersection over Union (IoU) threshold of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, and 0.7, respectively., Comment: Accepted to IEEE ACCESS

Healthcare data is sensitive and requires great protection. Encrypted electronic health records (EHRs) contain personal and sensitive data such as names and addresses. Having access to patient data benefits all of them. This paper proposes a blockchain-based distributed healthcare application platform for Bangladeshi public and private healthcare providers. Using data immutability and smart contracts, the suggested application framework allows users to create safe digital agreements for commerce or collaboration. Thus, all enterprises may securely collaborate using the same blockchain network, gaining data openness and read/write capacity. The proposed application consists of various application interfaces for various system users. For data integrity, privacy, permission and service availability, the proposed solution leverages Hyperledger fabric and Blockchain as a Service. Everyone will also have their own profile in the portal. A unique identity for each person and the installation of digital information centres across the country have greatly eased the process. It will collect systematic health data from each person which will be beneficial for research institutes and health-related organisations. A national data warehouse in Bangladesh is feasible for this application and It is also possible to keep a clean health sector by analysing data stored in this warehouse and conducting various purification algorithms using technologies like Data Science. Given that Bangladesh has both public and private health care, a straightforward digital strategy for all organisations is essential., Comment: 21 pages, 16 figures, 4 tables

When visualizing a high-dimensional dataset, dimension reduction techniques are commonly employed which provide a single 2-dimensional view of the data. We describe ENS-t-SNE: an algorithm for Embedding Neighborhoods Simultaneously that generalizes the t-Stochastic Neighborhood Embedding approach. By using different viewpoints in ENS-t-SNE's 3D embedding, one can visualize different types of clusters within the same high-dimensional dataset. This enables the viewer to see and keep track of the different types of clusters, which is harder to do when providing multiple 2D embeddings, where corresponding points cannot be easily identified. We illustrate the utility of ENS-t-SNE with real-world applications and provide an extensive quantitative evaluation with datasets of different types and sizes.

We describe MPSE: a Multi-Perspective Simultaneous Embedding method for visualizing high-dimensional data, based on multiple pairwise distances between the data points. Specifically, MPSE computes positions for the points in 3D and provides different views into the data by means of 2D projections (planes) that preserve each of the given distance matrices. We consider two versions of the problem: fixed projections and variable projections. MPSE with fixed projections takes as input a set of pairwise distance matrices defined on the data points, along with the same number of projections and embeds the points in 3D so that the pairwise distances are preserved in the given projections. MPSE with variable projections takes as input a set of pairwise distance matrices and embeds the points in 3D while also computing the appropriate projections that preserve the pairwise distances. The proposed approach can be useful in multiple scenarios: from creating simultaneous embedding of multiple graphs on the same set of vertices, to reconstructing a 3D object from multiple 2D snapshots, to analyzing data from multiple points of view. We provide a functional prototype of MPSE that is based on an adaptive and stochastic generalization of multi-dimensional scaling to multiple distances and multiple variable projections. We provide an extensive quantitative evaluation with datasets of different sizes and using different number of projections, as well as several examples that illustrate the quality of the resulting solutions.

Symmetry is a key feature observed in nature (from flowers and leaves, to butterflies and birds) and in human-made objects (from paintings and sculptures, to manufactured objects and architectural design). Rotational, translational, and especially reflectional symmetries, are also important in drawings of graphs. Detecting and classifying symmetries can be very useful in algorithms that aim to create symmetric graph drawings and in this paper we present a machine learning approach for these tasks. Specifically, we show that deep neural networks can be used to detect reflectional symmetries with 92% accuracy. We also build a multi-class classifier to distinguish between reflectional horizontal, reflectional vertical, rotational, and translational symmetries. Finally, we make available a collection of images of graph drawings with specific symmetric features that can be used in machine learning systems for training, testing and validation purposes. Our datasets, best trained ML models, source code are available online., Comment: Appears in the Proceedings of the 27th International Symposium on Graph Drawing and Network Visualization (GD 2019)

A \emph{Stick graph} is an intersection graph of axis-aligned segments such that the left end-points of the horizontal segments and the bottom end-points of the vertical segments lie on a `ground line,' a line with slope $-1$. It is an open question to decide in polynomial time whether a given bipartite graph $G$ with bipartition $A\cup B$ has a Stick representation where the vertices in $A$ and $B$ correspond to horizontal and vertical segments, respectively. We prove that $G$ has a Stick representation if and only if there are orderings of $A$ and $B$ such that $G$'s bipartite adjacency matrix with rows $A$ and columns $B$ excludes three small `forbidden' submatrices. This is similar to characterizations for other classes of bipartite intersection graphs. We present an algorithm to test whether given orderings of $A$ and $B$ permit a Stick representation respecting those orderings, and to find such a representation if it exists. The algorithm runs in time linear in the size of the adjacency matrix. For the case when only the ordering of $A$ is given, we present an $O(|A|^3|B|^3)$-time algorithm. When neither ordering is given, we present some partial results about graphs that are, or are not, Stick representable., Comment: Appears in the Proceedings of the 26th International Symposium on Graph Drawing and Network Visualization (GD 2018)

In this paper we describe a system for visualizing and analyzing worldwide research topics, {\tt rtopmap}. We gather data from google scholar academic research profiles, putting together a weighted topics graph, consisting of over 35,000 nodes and 646,000 edges. The nodes correspond to self-reported research topics, and edges correspond to co-occurring topics in google scholar profiles. The {\tt rtopmap} system supports zooming/panning/searching and other google-maps-based interactive features. With the help of map overlays, we also visualize the strengths and weaknesses of different academic institutions in terms of human resources (e.g., number of researchers in different areas), as well as scholarly output (e.g., citation counts in different areas). Finally, we also visualize what parts of the map are associated with different academic departments, or with specific documents (such as research papers, or calls for proposals). The system itself is available at \url{http://rtopmap.arl.arizona.edu/}.

In an $\mathsf{L}$-embedding of a graph, each vertex is represented by an $\mathsf{L}$-segment, and two segments intersect each other if and only if the corresponding vertices are adjacent in the graph. If the corner of each $\mathsf{L}$-segment in an $\mathsf{L}$-embedding lies on a straight line, we call it a monotone $\mathsf{L}$-embedding. In this paper we give a full characterization of monotone $\mathsf{L}$-embeddings by introducing a new class of graphs which we call "non-jumping" graphs. We show that a graph admits a monotone $\mathsf{L}$-embedding if and only if the graph is a non-jumping graph. Further, we show that outerplanar graphs, convex bipartite graphs, interval graphs, 3-leaf power graphs, and complete graphs are subclasses of non-jumping graphs. Finally, we show that distance-hereditary graphs and $k$-leaf power graphs ($k\le 4$) admit $\mathsf{L}$-embeddings.