arXiv subjects

Georgios Theodoropoulos

Publications and source records attributed to Georgios Theodoropoulos.

29 records · Page 2Linked to original sources

arXiv2021

Time-Efficient and High-Quality Graph Partitioning for Graph Dynamic Scaling

The dynamic scaling of distributed computations plays an important role in the utilization of elastic computational resources, such as the cloud. It enables the provisioning and de-provisioning of resources to match dynamic resource availability and demands. In the case of distributed graph processing, changing the number of the graph partitions while maintaining high partitioning quality imposes serious computational overheads as typically a time-consuming graph partitioning algorithm needs to execute each time repartitioning is required. In this paper, we propose a dynamic scaling method that can efficiently change the number of graph partitions while keeping its quality high. Our idea is based on two techniques: preprocessing and very fast edge partitioning, called graph edge ordering and chunk-based edge partitioning, respectively. The former converts the graph data into an ordered edge list in such a way that edges with high locality are closer to each other. The latter immediately divides the ordered edge list into an arbitrary number of high-quality partitions. The evaluation with the real-world billion-scale graphs demonstrates that our proposed approach significantly reduces the repartitioning time, while the partitioning quality it achieves is on par with that of the best existing static method.

cs.DC↗

arXiv2020

A Fuzzy Logic Controller for Tasks Scheduling Using Unreliable Cloud Resources

The Cloud infrastructure offers to end users a broad set of heterogenous computational resources using the pay-as-you-go model. These virtualized resources can be provisioned using different pricing models like the unreliable model where resources are provided at a fraction of the cost but with no guarantee for an uninterrupted processing. However, the enormous gamut of opportunities comes with a great caveat as resource management and scheduling decisions are increasingly complicated. Moreover, the presented uncertainty in optimally selecting resources has also a negatively impact on the quality of solutions delivered by scheduling algorithms. In this paper, we present a dynamic scheduling algorithm (i.e., the Uncertainty-Driven Scheduling - UDS algorithm) for the management of scientific workflows in Cloud. Our model minimizes both the makespan and the monetary cost by dynamically selecting reliable or unreliable virtualized resources. For covering the uncertainty in decision making, we adopt a Fuzzy Logic Controller (FLC) to derive the pricing model of the resources that will host every task. We evaluate the performance of the proposed algorithm using real workflow applications being tested under the assumption of different probabilities regarding the revocation of unreliable resources. Numerical results depict the performance of the proposed approach and a comparative assessment reveals the position of the paper in the relevant literature.

cs.DC↗

arXiv2020

Online NEAT for Credit Evaluation -- a Dynamic Problem with Sequential Data

In this paper, we describe application of Neuroevolution to a P2P lending problem in which a credit evaluation model is updated based on streaming data. We apply the algorithm Neuroevolution of Augmenting Topologies (NEAT) which has not been widely applied generally in the credit evaluation domain. In addition to comparing the methodology with other widely applied machine learning techniques, we develop and evaluate several enhancements to the algorithm which make it suitable for the particular aspects of online learning that are relevant in the problem. These include handling unbalanced streaming data, high computation costs, and maintaining model similarity over time, that is training the stochastic learning algorithm with new data but minimizing model change except where there is a clear benefit for model performance

cs.LG↗

arXiv2019

Performance Evaluation of Dynamic Scaling on MPI

Dynamic scaling aims to elastically change the number of processes during runtime to tune the performance of the distributed applications. This report briefly presents a performance evaluation of MPI process provisioning / de-provisioning for dynamic scaling by using 16 to 128 cores. Our dynamic scaling implementation allows the new MPI processes from new hosts to communicate with the original ones immediately. Moreover, it forbids the removing MPI processes to communicate with others as well as gets the information whether the host node can be terminated or not. Such a simple feature is not supported as a single-line API in MPI-2 such as MPI_Comm_spawn(). We provide our implementation as a simple library to extend a non-dynamic-scalable MPI program into a dynamic-scalable one by adding only several lines of codes.

cs.DC↗

arXiv2019

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal infernce tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are reinforced by extensive experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, out-performing them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters.

cs.SI↗

arXiv2019

Distributed Edge Partitioning for Trillion-edge Graphs

We propose Distributed Neighbor Expansion (Distributed NE), a parallel and distributed graph partitioning method that can scale to trillion-edge graphs while providing high partitioning quality. Distributed NE is based on a new heuristic, called parallel expansion, where each partition is constructed in parallel by greedily expanding its edge set from a single vertex in such a way that the increase of the vertex cuts becomes local minimal. We theoretically prove that the proposed method has the upper bound in the partitioning quality. The empirical evaluation with various graphs shows that the proposed method produces higher-quality partitions than the state-of-the-art distributed graph partitioning algorithms. The performance evaluation shows that the space efficiency of the proposed method is an order-of-magnitude better than the existing algorithms, keeping its time efficiency comparable. As a result, Distributed NE can partition a trillion-edge graph using only 256 machines within 70 minutes.

cs.DC↗

arXiv2019

TMIXT: A process flow for Transcribing MIXed handwritten and machine-printed Text

Handling large corpuses of documents is of significant importance in many fields, no more so than in the areas of crime investigation and defence, where an organisation may be presented with a large volume of scanned documents which need to be processed in a finite time. However, this problem is exacerbated both by the volume, in terms of scanned documents and the complexity of the pages, which need to be processed. Often containing many different elements, which each need to be processed and understood. Text recognition, which is a primary task of this process, is usually dependent upon the type of text, being either handwritten or machine-printed. Accordingly, the recognition involves prior classification of the text category, before deciding on the recognition method to be applied. This poses a more challenging task if a document contains both handwritten and machine-printed text. In this work, we present a generic process flow for text recognition in scanned documents containing mixed handwritten and machine-printed text without the need to classify text in advance. We realize the proposed process flow using several open-source image processing and text recognition packages1. The evaluation is performed using a specially developed variant, presented in this work, of the IAM handwriting database, where we achieve an average transcription accuracy of nearly 80% for pages containing both printed and handwritten text.

cs.LG↗

arXiv2018

Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning

Graphs are a commonly used construct for representing relationships between elements in complex high dimensional datasets. Many real-world phenomenon are dynamic in nature, meaning that any graph used to represent them is inherently temporal. However, many of the machine learning models designed to capture knowledge about the structure of these graphs ignore this rich temporal information when creating representations of the graph. This results in models which do not perform well when used to make predictions about the future state of the graph -- especially when the delta between time stamps is not small. In this work, we explore a novel training procedure and an associated unsupervised model which creates graph representations optimised to predict the future state of the graph. We make use of graph convolutional neural networks to encode the graph into a latent representation, which we then use to train our temporal offset reconstruction method, inspired by auto-encoders, to predict a later time point -- multiple time steps into the future. Using our method, we demonstrate superior performance for the task of future link prediction compared with none-temporal state-of-the-art baselines. We show our approach to be capable of outperforming non-temporal baselines by 38% on a real world dataset.

cs.SI↗

arXiv2018

Exploring the Semantic Content of Unsupervised Graph Embeddings: An Empirical Study

Graph embeddings have become a key and widely used technique within the field of graph mining, proving to be successful across a broad range of domains including social, citation, transportation and biological. Graph embedding techniques aim to automatically create a low-dimensional representation of a given graph, which captures key structural elements in the resulting embedding space. However, to date, there has been little work exploring exactly which topological structures are being learned in the embeddings process. In this paper, we investigate if graph embeddings are approximating something analogous with traditional vertex level graph features. If such a relationship can be found, it could be used to provide a theoretical insight into how graph embedding approaches function. We perform this investigation by predicting known topological features, using supervised and unsupervised methods, directly from the embedding space. If a mapping between the embeddings and topological features can be found, then we argue that the structural information encapsulated by the features is represented in the embedding space. To explore this, we present extensive experimental evaluation from five state-of-the-art unsupervised graph embedding techniques, across a range of empirical graph datasets, measuring a selection of topological features. We demonstrate that several topological features are indeed being approximated by the embedding space, allowing key insight into how graph embeddings create good representations.

cs.LG↗

arXiv2014

Scalable RDF Data Compression using X10

The Semantic Web comprises enormous volumes of semi-structured data elements. For interoperability, these elements are represented by long strings. Such representations are not efficient for the purposes of Semantic Web applications that perform computations over large volumes of information. A typical method for alleviating the impact of this problem is through the use of compression methods that produce more compact representations of the data. The use of dictionary encoding for this purpose is particularly prevalent in Semantic Web database systems. However, centralized implementations present performance bottlenecks, giving rise to the need for scalable, efficient distributed encoding schemes. In this paper, we describe an encoding implementation based on the asynchronous partitioned global address space (APGAS) parallel programming model. We evaluate performance on a cluster of up to 384 cores and datasets of up to 11 billion triples (1.9 TB). Compared to the state-of-art MapReduce algorithm, we demonstrate a speedup of 2.6-7.4x and excellent scalability. These results illustrate the strong potential of the APGAS model for efficient implementation of dictionary encoding and contributes to the engineering of larger scale Semantic Web applications.

cs.DC↗

arXiv2012

A General Methodology for the Determination of 2D Bodies Elastic Deformation Invariants. Application to the Automatic Identification of Parasites

A novel methodology is introduced here that exploits 2D images of arbitrary elastic body deformation instances, so as to quantify mechano-elastic characteristics that are deformation invariant. Determination of such characteristics allows for developing methods offering an image of the undeformed body. General assumptions about the mechano-elastic properties of the bodies are stated, which lead to two different approaches for obtaining bodies' deformation invariants. One was developed to spot deformed body's neutral line and its cross sections, while the other solves deformation PDEs by performing a set of equivalent image operations on the deformed body images. Both these processes may furnish a body undeformed version from its deformed image. This was confirmed by obtaining the undeformed shape of deformed parasites, cells (protozoa), fibers and human lips. In addition, the method has been applied to the important problem of parasite automatic classification from their microscopic images. To achieve this, we first apply the previous method to straighten the highly deformed parasites and then we apply a dedicated curve classification method to the straightened parasite contours. It is demonstrated that essentially different deformations of the same parasite give rise to practically the same undeformed shape, thus confirming the consistency of the introduced methodology. Finally, the developed pattern recognition method classifies the unwrapped parasites into 6 families, with an accuracy rate of 97.6 %.

cs.CV↗