Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Ferhatosmanoǧlu, Hakan"'
Publikováno v:
Proc. VLDB Endow. 17, 11 (2024), 2764-2777
Graph Neural Network (GNN) models on streaming graphs entail algorithmic challenges to continuously capture its dynamic state, as well as systems challenges to optimize latency, memory, and throughput during both inference and training. We present D3
Externí odkaz:
http://arxiv.org/abs/2409.09079
Autor:
Oakley, Joe, Ferhatosmanoglu, Hakan
Serverless computing offers attractive scalability, elasticity and cost-effectiveness. However, constraints on memory, CPU and function runtime have hindered its adoption for data-intensive applications and machine learning (ML) workloads. Traditiona
Externí odkaz:
http://arxiv.org/abs/2403.15195
Publikováno v:
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM '23), October 21--25, 2023, Birmingham, United Kingdom
Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of efficiency and accuracy for large and deep GNNs. We present an end-to-e
Externí odkaz:
http://arxiv.org/abs/2308.14949
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary. Since the convolution opera
Externí odkaz:
http://arxiv.org/abs/2212.05009
While machine learning and ranking-based systems are in widespread use for sensitive decision-making processes (e.g., determining job candidates, assigning credit scores), they are rife with concerns over unintended biases in their outcomes, which ma
Externí odkaz:
http://arxiv.org/abs/2208.14175
Synthetic data generation is a fundamental task for many data management and data science applications. Spatial data is of particular interest, and its sensitive nature often leads to privacy concerns. We introduce GeoPointGAN, a novel GAN-based solu
Externí odkaz:
http://arxiv.org/abs/2205.08886
Current approaches for modeling propagation in networks (e.g., spread of disease) are unable to adequately capture temporal properties of the data such as order and duration of evolving connections or dynamic likelihoods of propagation along these co
Externí odkaz:
http://arxiv.org/abs/2203.14925
Shortest path queries over graphs are usually considered as isolated tasks, where the goal is to return the shortest path for each individual query. In practice, however, such queries are typically part of a system (e.g., a road network) and their ex
Externí odkaz:
http://arxiv.org/abs/2110.09937
Publikováno v:
17th International Symposium on Spatial and Temporal Databases (SSTD '21), 2021
Sharing sensitive data is vital in enabling many modern data analysis and machine learning tasks. However, current methods for data release are insufficiently accurate or granular to provide meaningful utility, and they carry a high risk of deanonymi
Externí odkaz:
http://arxiv.org/abs/2108.02089
Publikováno v:
PVLDB, 14(11): 2283 - 2295, 2021
Sharing trajectories is beneficial for many real-world applications, such as managing disease spread through contact tracing and tailoring public services to a population's travel patterns. However, public concern over privacy and data protection has
Externí odkaz:
http://arxiv.org/abs/2108.02084