Accès ouvert
2026
preprint
OpenAlex
Nicholas Majeske, Ariful Azad
Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future …
Accès ouvert
2026
preprint
OpenAlex
Nicholas Majeske, Ariful Azad
Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future …
us
(code pays fourni par la source)
Accès ouvert
2026
conference-paper
OpenAlex
Matthew Qian, Yahia Ramadan, Suhita Anubha, Ariful Azad
Sparse matrix-dense matrix multiplication (SpMM) is a critical kernel in scientific computing, graph analytics, and machine learning, whose performance is often constrained by memory bandwidth. In this work, we investigate the applicability and limitations of roofline modeling for SpMM by explicitly accounting …
us
(code pays fourni par la source)
Accès ouvert
2026
conference-paper
OpenAlex
Selahattin Akkas, Ariful Azad
We consider the problem of graph sparsification while preserving the test accuracy of Graph Neural Networks (GNNs). Prior work in this area is often motivated by the Lottery Ticket Hypothesis, which aims to prune redundant edges. However, these sparsification approaches typically operate …
us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Matthew Qian, Yahia Ramadan, Suhita Anubha, Ariful Azad
Sparse matrix-dense matrix multiplication (SpMM) is a critical kernel in scientific computing, graph analytics, and machine learning, whose performance is often constrained by memory bandwidth. In this work, we investigate the applicability and limitations of roofline modeling for SpMM by explicitly accounting …
us
(code pays fourni par la source)
2025
conference-paper
OpenAlex
Isuru Ranawaka, Ariful Azad
We develop a distributed-memory algorithm to embed nodes of a graph into a low-dimensional vector space. Our distributed algorithm, called DistFNE, is based on a force-directed layout that maximizes attraction among neighboring vertices and repulsion among distant ones. DistFNE utilizes large minibatches …
us
(code pays fourni par la source)
Accès ouvert
2025
preprint
OpenAlex
Elaheh Hassani, Md Taufique Hussain, Ariful Azad
We present scalable distributed-memory algorithms for sparse matrix permutation, extraction, and assignment. Our methods follow an Identify-Exchange-Build (IEB) strategy where each process identifies the local nonzeros to be sent, exchanges the required data, and then builds its local submatrix from the received …
Accès ouvert
2025
preprint
OpenAlex
Selahattin Akkas, Aditya Devarakonda, Ariful Azad
With the growing adoption of graph neural networks (GNNs), explaining their predictions has become increasingly important. However, attributing predictions to specific edges or features remains computationally expensive. For example, classifying a node with 100 neighbors using a 3-layer GNN may involve identifying …
Accès ouvert
2025
preprint
OpenAlex
Qi Yu, Zhichen Zeng, Yuchen Yan, Zhining Liu et autres
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. Despite growing research in NA, there lacks a comprehensive library that facilitates the systematic development and benchmarking of NA …
Accès ouvert
2025
article
OpenAlex
Nicholas Majeske, Shreyas Sunil Vaidya, Ryan Roy, Abdul Rehman et autres
We develop a comprehensive framework for storing, analyzing, forecasting, and visualizing industrial energy systems consisting of multiple devices and sensors. Our framework models complex energy systems as a dynamic knowledge graph, utilizes a novel machine learning (ML) model for energy forecasting, and …
us
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Dipta Paul, S M Aliuzzaman, Mohammed R. Ali, Ahatesham Rabbi et autres
In today's era of rapid advancement in technology, innovative assistive devices are transforming accessibility for visually impaired. Through the integration of assistive health technologies, embedded systems, and software engineering, the Smart Assistive Stick enables people to navigate on their own. Fundamentally, an …
Accès ouvert
2025
article
OpenAlex
Dipta Paul, S M Aliuzzaman, Mohammed R. Ali, Ahatesham Rabbi et autres
In today's era of rapid advancement in technology, innovative assistive devices are transforming accessibility for visually impaired. Through the integration of assistive health technologies, embedded systems, and software engineering, the Smart Assistive Stick enables people to navigate on their own. Fundamentally, an …