Gunduz Vehbi Demirci

Gunduz Vehbi Demirci

Auto-generated profile, based on publicly available information

Gunduz Vehbi Demirci

Imagination Technologies, Coventry, UK

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 April 2023 in ACM Transactions on Spatial Algorithms and Systems
Verified
Journal Article
Open access
AHAparajita Haldar
Aparajita Haldar
SWShuang Wang
Shuang Wang
GDGunduz Vehbi Demirci
Gunduz Vehbi Demirci
JOJoe Oakley
Joe Oakley
HFHakan Ferhatosmanoglu
Hakan Ferhatosmanoglu
Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections. Temporal models on evolving networks are crucial in applications that need to analyze dynamic spread. For example, a disease spreading virus has varying transmissibility based on interactions between individuals occurring with different frequency, proximity, and venue population density. Similarly, propagation of information having a limited active period, such as rumors, depends on the temporal dynamics of social interactions. To capture such behaviors, we first develop the Temporal Independent Cascade (T-IC) model with a spread function that efficiently utilizes a hypergraph-based sampling strategy and dynamic propagation probabilities. We prove this function to be submodular, with guarantees of approximation quality. This enables scalable analysis on highly granular temporal networks where other models struggle, such as when the spread across connections exhibits arbitrary temporally evolving patterns. We then introduce the notion of “reverse spread” using the proposed T-IC processes, and develop novel solutions to identify both sentinel/detector nodes and highly susceptible nodes. Extensive analysis on real-world datasets shows that the proposed approach significantly outperforms the alternatives in modeling both if and how spread occurs, by considering evolving network topology alongside granular contact/interaction information. Our approach has numerous applications, such as virus/rumor/influence tracking. Utilizing T-IC, we explore vital challenges of monitoring the impact of various intervention strategies over real spatio-temporal contact networks where we show our approach to be highly effective.

8 June 2020 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
GDGunduz Vehbi Demirci
Gunduz Vehbi Demirci
CACevdet Aykanat
Cevdet Aykanat
The focus is distributed-memory parallelization of sparse-general-matrix-multiplication (SpGEMM). Parallel SpGEMM algorithms are classified under one-dimensional (1D), 2D, and 3D categories denoting the number of dimensions by which the 3D sparse workcube representing the iteration space of SpGEMM is partitioned. Recently proposed successful 2D- and 3D-parallel SpGEMM algorithms benefit from upper bounds on communication overheads enforced by 2D and 3D cartesian partitioning of the workcube on 2D and 3D virtual processor grids, respectively. However, these methods are based on random cartesian partitioning and do not utilize sparsity patterns of SpGEMM instances for reducing the communication overheads. We propose hypergraph models for 2D and 3D cartesian partitioning of the workcube for further reducing the communication overheads of these 2D- and 3D- parallel SpGEMM algorithms. The proposed models utilize two- and three-phase partitioning that exploit multi-constraint hypergraph partitioning formulations. Extensive experimentation performed on 20 SpGEMM instances by using upto 900 processors demonstrate that proposed partitioning models significantly improve the scalability of 2D and 3D algorithms. For example, in 2D-parallel SpGEMM algorithm on 900 processors, the proposed partitioning model respectively achieves 85 and 42 percent decrease in total volume and total number of messages, leading to 1.63 times higher speedup compared to random partitioning, on average.

13 December 2018 in The VLDB Journal
Verified
Journal Article
Open access
PDF file
GDGunduz Vehbi Demirci
Gunduz Vehbi Demirci
HFHakan Ferhatosmanoglu
Hakan Ferhatosmanoglu
CACevdet Aykanat
Cevdet Aykanat
Graph partitioning is an essential task for scalable data management and analysis. The current partitioning methods utilize the structure of the graph, and the query log if available. Some queries performed on the database may trigger further operations. For example, the query workload of a social network application may contain re-sharing operations in the form of cascades. It is beneficial to include the potential cascades in the graph partitioning objectives. In this paper, we introduce the problem of cascade-aware graph partitioning that aims to minimize the overall cost of communication among parts/servers during cascade processes. We develop a randomized solution that estimates the underlying cascades, and use it as an input for partitioning of large-scale graphs. Experiments on 17 real social networks demonstrate the effectiveness of the proposed solution in terms of the partitioning objectives.