2 code implementations • 4 May 2023 • Tim Kaler, Alexandros-Stavros Iliopoulos, Philip Murzynowski, Tao B. Schardl, Charles E. Leiserson, Jie Chen
To significantly reduce the communication volume without compromising prediction accuracy, we propose a policy for caching data associated with frequently accessed vertices in remote partitions.
1 code implementation • 16 Oct 2021 • Tim Kaler, Nickolas Stathas, Anne Ouyang, Alexandros-Stavros Iliopoulos, Tao B. Schardl, Charles E. Leiserson, Jie Chen
Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the exponential growth of multi-hop graph neighborhoods along network layers.
no code implementations • 4 Feb 2021 • Dimitris Floros, Mulugu V. Brahmajothi, Alexandros-Stavros Iliopoulos, Nikos Pitsianis, Xiaobai Sun
We translate, encode and implement the principles in the platform with novel use of advanced concepts and techniques to ensure and protect data integrity and research integrity.
Computers and Society
no code implementations • 20 Aug 2020 • Wanyi Fu, Shobhit Sharma, Ehsan Abadi, Alexandros-Stavros Iliopoulos, Qi. Wang, Joseph Y. Lo, Xiaobai Sun, William P. Segars, Ehsan Samei
Objective: This study aims to develop and validate a novel framework, iPhantom, for automated creation of patient-specific phantoms or digital-twins (DT) using patient medical images.
no code implementations • 13 Jun 2019 • Nikos Pitsianis, Alexandros-Stavros Iliopoulos, Dimitris Floros, Xiaobai Sun
We introduce a nonlinear method for directly embedding large, sparse, stochastic graphs into low-dimensional spaces, without requiring vertex features to reside in, or be transformed into, a metric space.
no code implementations • 12 Sep 2017 • Nikos Pitsianis, Dimitris Floros, Alexandros-Stavros Iliopoulos, Kostas Mylonakis, Nikos Sismanis, Xiaobai Sun
The method is distinguished by the guiding principle to obtain a profile that is block-sparse with dense blocks.
1 code implementation • 27 Oct 2016 • Abhishek Kumar Dubey, Alexandros-Stavros Iliopoulos, Xiaobai Sun, Fang-Fang Yin, Lei Ren
Conclusion: Our analysis captures properties of DVF data associated with clinical CT images, and provides new understanding of iterative DVF inversion algorithms with a simple residual feedback control.
no code implementations • 3 Jun 2015 • Alexandros-Stavros Iliopoulos, Tiancheng Liu, Xiaobai Sun
We present a new and effective approach for Hyperspectral Image (HSI) classification and clutter detection, overcoming a few long-standing challenges presented by HSI data characteristics.