6 citations · 21 across the 34 of their papers we have counts for
17 papers · 1 filter
Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours
Yuxin Yang, Hongkuan Zhou, Rajgopal Kannan +1
Temporal Graph Neural Networks (TGNNs) have emerged as powerful tools for modeling dynamic interactions across various domains. The design space of TGNNs is notably complex, given…
Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
Tian Ye, Rajgopal Kannan, Viktor Prasanna
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled d…
Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information
Ömer Faruk Akgül, Rajgopal Kannan, Viktor Prasanna
Graphs play a crucial role in data mining and machine learning, representing real-world objects and interactions. As graph datasets grow, managing large, decentralized subgraphs be…
Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
Gangda Deng, Hongkuan Zhou, Rajgopal Kannan +1
Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs). Increasing the GNN depth can expand the scope (i.e., receptive fiel…
Studying the Effects of Self-Attention on SAR Automatic Target Recognition
Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna
Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often stru…
Sparse MTTKRP Acceleration for Tensor Decomposition on GPU
Sasindu Wijeratne, Rajgopal Kannan, Viktor Prasanna
Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the bottleneck kernel of sparse tensor decomposition. In this work, we propose a GPU-based algorithm design to addre…
Accelerating ViT Inference on FPGA through Static and Dynamic Pruning
Dhruv Parikh, Shouyi Li, Bingyi Zhang +3
Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied t…
GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Bingyi Zhang, Rajgopal Kannan, Carl Busart +1
Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers…
TabConv: Low-Computation CNN Inference via Table Lookups
Neelesh Gupta, Narayanan Kannan, Pengmiao Zhang +1
Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic oper…
VTR: An Optimized Vision Transformer for SAR ATR Acceleration on FPGA
Sachini Wickramasinghe, Dhruv Parikh, Bingyi Zhang +3
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is a key technique used in military applications like remote-sensing image recognition. Vision Transformers (ViTs)…
FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification
Xu Wang, Tian Ye, Rajgopal Kannan +1
Deep Learning (DL) Models for Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), while delivering improved performance, have been shown to be quite vulnerable to ad…
Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks
Tian Ye, Rajgopal Kannan, Viktor Prasanna +1
Adversarial attacks have demonstrated the vulnerability of Machine Learning (ML) image classifiers in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems. An…
Attention, Distillation, and Tabularization: Towards Practical Neural Network-Based Prefetching
Pengmiao Zhang, Neelesh Gupta, Rajgopal Kannan +1
Attention-based Neural Networks (NN) have demonstrated their effectiveness in accurate memory access prediction, an essential step in data prefetching. However, the substantial com…
PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models
Neelesh Gupta, Pengmiao Zhang, Rajgopal Kannan +1
Deep neural networks (DNNs) have proven to be effective models for accurate Memory Access Prediction (MAP), a critical task in mitigating memory latency through data prefetching. H…
ME-ViT: A Single-Load Memory-Efficient FPGA Accelerator for Vision Transformers
Kyle Marino, Pengmiao Zhang, Viktor Prasanna
Vision Transformers (ViTs) have emerged as a state-of-the-art solution for object classification tasks. However, their computational demands and high parameter count make them unsu…
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning
Gangda Deng, Hongkuan Zhou, Hanqing Zeng +5
Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommend…
A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification
Jacob Fein-Ashley, Sachini Wickramasinghe, Bingyi Zhang +2
Image classifiers for domain-specific tasks like Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) and chest X-ray classification often rely on convolutional neural n…