no code implementations • 22 Mar 2024 • Joe Oakley, Hakan Ferhatosmanoglu
In the absence of such solutions in the serverless domain, parallel computation with significant IPC requirements is challenging.
1 code implementation • 29 Aug 2023 • Shuang Wang, Bahaeddin Eravci, Rustam Guliyev, Hakan Ferhatosmanoglu
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.
no code implementations • 9 Dec 2022 • Gunduz Vehbi Demirci, Aparajita Haldar, Hakan Ferhatosmanoglu
The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary.
no code implementations • 30 Aug 2022 • Aparajita Haldar, Teddy Cunningham, Hakan Ferhatosmanoglu
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 makes algorithmic fairness (e. g., demographic parity, equal opportunity) an objective of interest.
1 code implementation • 18 May 2022 • Teddy Cunningham, Konstantin Klemmer, Hongkai Wen, Hakan Ferhatosmanoglu
We introduce GeoPointGAN, a novel GAN-based solution for generating synthetic spatial point datasets with high utility and strong individual level privacy guarantees.
no code implementations • 23 Apr 2021 • Gunduz Vehbi Demirci, Hakan Ferhatosmanoglu
Both the feedforward (inference) and backpropagation steps in stochastic gradient descent (SGD) algorithm for training sparse DNNs involve consecutive sparse matrix-vector multiplications (SpMVs).
no code implementations • 2 Sep 2019 • Sreyasi Nag Chowdhury, Niket Tandon, Hakan Ferhatosmanoglu, Gerhard Weikum
CBIR now gains semantic expressiveness by advances in deep-learning-based detection of visual labels.
2 code implementations • WS 2019 • Brendan Whitaker, Denis Newman-Griffis, Aparajita Haldar, Hakan Ferhatosmanoglu, Eric Fosler-Lussier
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors.