Search

Copyright of Firat Universitesi Sağlik Bilimleri Tip Dergisi is the property of Firat Universitesiu, Saglik Bilimleri Enstitusu and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Summary: This is an editorial for the Special Issue on the 7th High‐Performance Computing Conference (BAŞARIM 2022) organized on May 11–13, 2022, at Sabanci University Altunizade Digital Campus, İstanbul. [ABSTRACT FROM AUTHOR]

Graphs are ubiquitous, and they can model unique characteristics and complex relations of real-life systems. Although using machine learning (ML) on graphs is promising, their raw representation is not suitable for ML algorithms. Graph embedding represents each node of a graph as a $d$ d -dimensional vector which is more suitable for ML tasks. However, the embedding process is expensive, and CPU-based tools do not scale to real-world graphs. In this work, we present GOSH, a GPU-based tool for embedding large-scale graphs with minimum hardware constraints. GOSH employs a novel graph coarsening algorithm to enhance the impact of updates and minimize the work for embedding. It also incorporates a decomposition schema that enables any arbitrarily large graph to be embedded with a single GPU. As a result, GOSH sets a new state-of-the-art in link prediction both in accuracy and speed, and delivers high-quality embeddings for node classification at a fraction of the time compared to the state-of-the-art. For instance, it can embed a graph with over 65 million vertices and 1.8 billion edges in less than 30 minutes on a single GPU. [ABSTRACT FROM AUTHOR]

Summary: For dynamic and continuous data analysis, conventional OLTP systems are slow in performance. Today's cutting‐edge high‐performance computing hardware, such as GPUs, has been used as accelerators for data analysis tasks, which traditionally leverage CPUs on classical database management systems (DBMS). When CPUs and GPUs are used together, the architectural heterogeneity, that is, leveraging hardware with different performance characteristics jointly, creates complex problems that need careful treatment for performance optimization. Load distribution and balancing are crucial problems for DBMSs working on heterogeneous architectures. In this work, focusing on a hybrid, CPU‐GPU database management system to process users' queries, we propose heuristical and machine‐learning‐based (ML‐based) load distribution and balancing models. In more detail, we employ multiple linear regression (MLR), random forest (RF), and Adaboost (Ada) models to dynamically decide the processing unit for each incoming query based on the response time predictions on both CPU and GPU. The ML‐based models outperformed the other algorithms, as well as the CPU and GPU‐only running modes with up to 27%, 29%, and 40%, respectively, in overall performance (response time) while answering intense real‐life working scenarios. Finally, we propose to use a hybrid load‐balancing model that would be more efficient than the models we tested in this work. [ABSTRACT FROM AUTHOR]

Influence maximization (IM) is the problem of finding a seed vertex set which is expected to incur the maximum influence spread on a graph. It has various applications in practice such as devising an effective and efficient approach to disseminate information, news or ad within a social network. The problem is shown to be NP-hard and approximation algorithms with provable quality guarantees exist in the literature. However, these algorithms are computationally expensive even for medium-scaled graphs. Furthermore, graph algorithms usually suffer from spatial and temporal irregularities during memory accesses, and this adds an extra cost on top of the already expensive IM kernels. In this article we leverage fused sampling, memoization, and vectorization to restructure, parallelize and boost their performance on undirected networks. The proposed approach employs a pseudo-random function and performs multiple Monte-Carlo simulations in parallel to exploit the SIMD lanes effectively and efficiently. In addition, it significantly reduces the number of edge traversals, hence the amount of data brought from the memory, which is critical for almost all memory-bound graph kernels. We apply the proposed approach to the traditional MixGreedy algorithm and propose INFuseR-MG which is more than $3000\times$ 3000 × faster than the greedy approaches and can run on large graphs that have been considered as too large in the literature. For instance, the new algorithm runs in 2.09, 0.08, 0.36 seconds on graphs Amazon, NetHEP, NetPhy with 16 threads where the sequential baseline takes 141.3, 259.1 and 1725.2 seconds, respectively. To compare INFuseR-MG with the state-of-the-art approximation algorithms, we conduct a thorough experimental analysis with various influence settings. The results on real-life, undirected networks show that on 16 threads, INFuseR-MG is $2.3\times$ 2. 3 × – $173.8\times$ 173. 8 × faster than state-of-the-art while being superior in terms of influence scores, and using a comparable amount of memory. [ABSTRACT FROM AUTHOR]

The permanent is an important characteristic of a matrix and it has been used in many applications. Unfortunately, it is a hard to compute and hard to approximate the immanant. For dense/full matrices, the fastest exact algorithm, Ryser, has O(2n-1n complexity. In this work, a parallel algorithm, SkipPer, is proposed to exploit the sparsity within the input matrix as much as possible. SkipPer restructures the matrix to reduce the overall work, skips the unnecessary steps, and employs a coarse-grain, shared-memory parallelization with dynamic scheduling. The experiments show that SkipPer increases the performance of exact permanent computation up to 140x compared to the naive version for general matrices. Furthermore, thanks to the coarse-grain parallelization, 14-15x speedup on average is obtained with β = 16 threads over sequential SkipPer. Overall, by exploiting the sparsity and parallelism, the speedup is 2000x for some of the matrices used in the experimental setting. The proposed techniques in this paper can be used to significantly improve the performance of exact permanent computation by simply replacing Ryser with SkipPer, especially when the matrix is highly sparse. [ABSTRACT FROM AUTHOR]

We investigate the problem of partitioning the vertices of a directed acyclic graph into a given number of parts. The objective function is to minimize the number or the total weight of the edges having end points in different parts, which is also known as the edge cut. The standard load balancing constraint of having an equitable partition of the vertices among the parts should be met. Furthermore, the partition is required to be acyclic; i.e., the interpart edges between the vertices from different parts should preserve an acyclic dependency structure among the parts. In this work, we adopt the multilevel approach with coarsening, initial partitioning, and refinement phases for acyclic partitioning of directed acyclic graphs. We focus on two-way partitioning (sometimes called bisection), as this scheme can be used in a recursive way for multiway partitioning. To ensure the acyclicity of the partition at all times, we propose novel and efficient coarsening and refinement heuristics. The quality of the computed acyclic partitions is assessed by computing the edge cut. We also propose effective ways to use the standard undirected graph partitioning methods in our multilevel scheme. We perform a large set of experiments on a dataset consisting of (i) graphs coming from an application and (ii) some others corresponding to matrices from a public collection. We report significant improvements compared to the current state of the art. [ABSTRACT FROM AUTHOR]

In multilevel secret sharing, a secret is shared among a set of hierarchically organized participants in a way that the members of the superior compartments are more powerful and can replace the participants of an inferior one to form an authorized coalition during secret reconstruction. In this work, we first show that the only existing multilevel threshold secret sharing scheme based on the Chinese Remainder Theorem (CRT) is not secure and fails to work with certain natural threshold settings on compartments. As the main contribution, we propose a secure CRT-based scheme that works for all threshold settings. In the proposed scheme, we employ a refined version of Asmuth-Bloom secret sharing with a special and generic Asmuth-Bloom sequence called the anchor sequence. [ABSTRACT FROM AUTHOR]

We propose Hessian Approximated Multiple Subsets Iteration (HAMSI), which is a generic second order incremental algorithm for solving large-scale partially separable convex and nonconvex optimization problems. The algorithm is based on a local quadratic approximation, and hence, allows incorporating curvature information to speed-up the convergence. HAMSI is inherently parallel and it scales nicely with the number of processors. We prove the convergence properties of our algorithm when the subset selection step is deterministic. Combined with techniques for effectively utilizing modern parallel computer architectures, we illustrate that a particular implementation of the proposed method based on L-BFGS updates converges more rapidly than a parallel gradient descent when both methods are used to solve large-scale matrix factorization problems. This performance gain comes only at the expense of using memory that scales linearly with the total size of the optimization variables. We conclude that HAMSI may be considered as a viable alternative in many large scale problems, where first order methods based on variants of gradient descent are applicable. [ABSTRACT FROM AUTHOR]

Lipmaa's Computational Private Information Retrieval (CPIR) protocol is probably the most bandwidth efficient method in the literature, although its computational complexity is a limiting factor for practical applications as it is based on expensive public key operations. Utilizing binary decision diagrams (Bdd) and the Damgård–Jurik cryptosystem, Lipmaa's CPIR performs three modular exponentiation operations per internal node in Bdd. In this paper, we present a new CPIR protocol, which reduces the number of exponentiation operations to 1 per first-level internal nodes and 2 per other internal nodes of the Bdd. For 1024-bit exponents (i.e. 80-bit security level) and 32 768 items, when compared with the fastest parallel implementation in the literature on four cores, reducing the number of exponentiations yields a 1.22× speedup and the multiexponentiation technique adds 2.23× more on top of that. Overall, when combined, reducing the number of exponentiations, multi-exponentiation, parallelization on four cores and the hybrid approach can provide more than 300× speedup compared to the sequential implementation of the original method. [ABSTRACT FROM AUTHOR]

The betweenness and closeness metrics are widely used metrics in many network analysis applications. Yet, they are expensive to compute. For that reason, making the betweenness and closeness centrality computations faster is an important and well-studied problem. In this work, we propose the framework BADIOS that manipulates the graph by compressing it and splitting into pieces so that the centrality computation can be handled independently for each piece. Experimental results show that the proposed techniques can be a great arsenal to reduce the centrality computation time for various types and sizes of networks. In particular, it reduces the betweenness centrality computation time of a 4.6 million edges graph from more than 5 days to less than 16 hours. For the same graph, the closeness computation time is decreased from more than 3 days to 6 hours (12.7x speedup). [ABSTRACT FROM AUTHOR]

For commitments on secrets, statistical hiding is a must when we are dealing with a long-term secret or when the secret domain is small enough for a brute-force attack by a powerful adversary. Unfortunately, all the Chinese Remainder Theorem-based verifiable secret sharing schemes in the literature are either insecure or suffer from the vulnerability of computationally hiding commitments. To the best of our knowledge, there exist five such studies where two of them were already proven to be insecure. In this work, we first show that two of the remaining schemes are also insecure, that is, the schemes reveal information on the secret even when the adversary is passive. In addition, the remaining one is only secure against a computationally bounded adversary which can be a problem for secret sharing schemes requiring long-term secret obscurity or using small secret domain. We propose a modification for the latter scheme and prove that the modified scheme is a secure verifiable secret sharing scheme against an unbounded adversary. Lastly, as an application, we show how to use the new scheme for joint random secret sharing and analyze the practicality and efficiency of the proposed schemes. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Viruses of influenza A subtype H7 can be highly pathogenic and periodically infect humans. For example, there have been numerous outbreaks of H7 in the Americas and Europe since 1996. More recently, a reassortant H7N9 has emerged among humans and birds during 2013-2014 in China, Taiwan and Hong Kong. This H7N9 genome consists of genetic segments that assort with H7 and H9 viruses previously circulating in chickens and wild birds in China and ducks in Korea. Epidemic risk modellers have used agricultural, climatic and demographic data to predict that the virus will spread to northern Vietnam via poultry. To shed light on the traffic of H7 viruses in general, we examine genetic segments of influenza that have assorted with many strains of H7 viruses dating back to 1902. We focus on use cases from the United States, Italy and China. We apply a novel metric, betweenness, an associated phylogenetic visualization technique, transmission networks, and compare these with another technique, route mapping. In contrast to traditional views, our results illustrate that segments that assort with H7 viruses are spread frequently between the Americas and Eurasia. In summary, genetic segments that historically assort with H7 influenza viruses have been spread from China to: Australia, Czech Republic, Denmark, Egypt, Germany, Hong Kong, Italy, Japan, Mongolia, the Netherlands, New Zealand, Pakistan, South Africa, South Korea, Spain, Sweden, the UK, the US, and Vietnam. [ABSTRACT FROM AUTHOR]

Literature search is one of the most important steps of academic research. With more than 100,000 papers published each year just in computer science, performing a complete literature search becomes a Herculean task. Some of the existing approaches and tools for literature search cannot compete with the characteristics of today’s literature, and they suffer from ambiguity and homonymy. Techniques based on citation information are more robust to the mentioned issues. Thus, we recently built a Web service called the advisor, which provides personalized recommendations to researchers based on their papers of interest. Since most recommendation methods may return redundant results, diversifying the results of the search process is necessary to increase the amount of information that one can reach via an automated search. This article targets the problem of result diversification in citation-based bibliographic search, assuming that the citation graph itself is the only information available and no categories or intents are known. The contribution of this work is threefold. We survey various random walk--based diversification methods and enhance them with the direction awareness property to allow users to reach either old, foundational (possibly well-cited and well-known) research papers or recent (most likely less-known) ones. Next, we propose a set of novel algorithms based on vertex selection and query refinement. A set of experiments with various evaluation criteria shows that the proposed γ-RLM algorithm performs better than the existing approaches and is suitable for real-time bibliographic search in practice. [ABSTRACT FROM AUTHOR]

Literature search is one of the most important steps of academic research. With more than 100,000 papers published each year just in computer science, performing a complete literature search becomes a Herculean task. Some of the existing approaches and tools for literature search cannot compete with the characteristics of today’s literature, and they suffer from ambiguity and homonymy. Techniques based on citation information are more robust to the mentioned issues. Thus, we recently built a Web service called the advisor, which provides personalized recommendations to researchers based on their papers of interest. Since most recommendation methods may return redundant results, diversifying the results of the search process is necessary to increase the amount of information that one can reach via an automated search. This article targets the problem of result diversification in citation-based bibliographic search, assuming that the citation graph itself is the only information available and no categories or intents are known. The contribution of this work is threefold. We survey various random walk--based diversification methods and enhance them with the direction awareness property to allow users to reach either old, foundational (possibly well-cited and well-known) research papers or recent (most likely less-known) ones. Next, we propose a set of novel algorithms based on vertex selection and query refinement. A set of experiments with various evaluation criteria shows that the proposed γ-RLM algorithm performs better than the existing approaches and is suitable for real-time bibliographic search in practice. [ABSTRACT FROM AUTHOR]

Graphs and matrices are widely used in algorithms for social network analyses. Since the number of interactions is much less than the possible number of interactions, the graphs and matrices used in the analyses are usually sparse. In this paper, we propose an efficient implementation of a sparse-matrix computation which arises in our publicly available citation recommendation service the advisor as well as in many other recommendation systems. The recommendation algorithm uses a sparse matrix generated from the citation graph. We observed that the nonzero pattern of this matrix is highly irregular and the computation suffers from high number of cache misses. We propose techniques for storing the matrix in memory efficiently and we reduced the number of cache misses with ordering and partitioning. Experimental results show that our techniques are highly efficient in reducing the query processing time which is highly crucial for a web service. [ABSTRACT FROM AUTHOR]

The elimination tree model for sparse unsymmetric matrices and an algorithm for constructing it have been recently proposed by Eisenstat and Liu [SIAM J. Matrix Anal. Appl., 26 (2005), pp. 686-705] and [SIAM J. Matrix Anal. Appl., 29 (2008), pp. 1363-1381]. The construction algorithm has a worst-case time complexity of Θ(mn) for an n X n unsymmetric matrix having m off-diagonal nonzeros. We propose another algorithm that has a worst-case time complexity of ...(mlogn). We compare the two algorithms experimentally and show that both algorithms are efficient in general. The algorithm of Eisenstat and Liu is faster in many practical cases, yet there are instances in which there is a significant difference between the running time of the two algorithms in favor of the one proposed here. [ABSTRACT FROM AUTHOR]

We consider the following task assignment problem. Communicating tasks are to be assigned to heterogeneous processors interconnected with a heterogeneous network. The objective is to minimize the total sum of the execution and communication costs. The problem is NP-hard. We present an exact algorithm based on the well-known A* search. We report simulation results over a wide range of parameters where the largest solved instance contains about three hundred tasks to be assigned to eight processors. [ABSTRACT FROM AUTHOR]

The scheduling of independent but file-sharing tasks on heterogeneous master-slave platforms has recently found important applications in Grid environments. The scheduling heuristics recently proposed for this problem are all constructive in nature and based on a common greedy criterion which depends on the momentary completion time values of the tasks. We show that this greedy decision criterion has shortcomings in exploiting the file-sharing interaction among tasks since completion time values are inadequate to extract the global view of this interaction. We propose a three-phase scheduling approach which involves initial task assignment, refinement, and execution ordering phases. For the refinement phase, we model the target application as a hypergraph and, with an elegant hypergraph-partitioning-like formulation, we propose using iterative-improvement-based heuristics for refining the task assignments according to two novel objective functions. Unlike the turnaround time, which is the actual schedule cost, the smoothness of proposed objective functions enables the use of iterative-improvement-based heuristics successfully since their effectiveness and efficiency depend on the smoothness of the objective function. Experimental results on a wide range of synthetically generated heterogeneous master-slave frameworks show that the proposed three-phase scheduling approach performs much better than the greedy constructive approach. [ABSTRACT FROM AUTHOR]