activity
20182021
most citedELF: An Early-Exiting Framework for Long-Tailed Classification

16 citations · 43 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG20211 cited

EnergyVis: Interactively Tracking and Exploring Energy Consumption for ML Models

Omar Shaikh, Jon Saad-Falcon, Austin P Wright +4

The advent of larger machine learning (ML) models have improved state-of-the-art (SOTA) performance in various modeling tasks, ranging from computer vision to natural language. As…

cs.LG2020

A Large-Scale Database for Graph Representation Learning

Scott Freitas, Yuxiao Dong, Joshua Neil +1

With the rapid emergence of graph representation learning, the construction of new large-scale datasets is necessary to distinguish model capabilities and accurately assess the str…

cs.HC20208 cited

Argo Lite: Open-Source Interactive Graph Exploration and Visualization in Browsers

Siwei Li, Zhiyan Zhou, Anish Upadhayay +7

Graph data have become increasingly common. Visualizing them helps people better understand relations among entities. Unfortunately, existing graph visualization tools are primaril…

cs.LG202016 cited

ELF: An Early-Exiting Framework for Long-Tailed Classification

Rahul Duggal, Scott Freitas, Sunny Dhamnani +2

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the major…

cs.CV2020

UnMask: Adversarial Detection and Defense Through Robust Feature Alignment

Scott Freitas, Shang-Tse Chen, Zijie J. Wang +1

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has dem…

eess.SP202015 cited

REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild

Rahul Duggal, Scott Freitas, Cao Xiao +2

In recent years, significant attention has been devoted towards integrating deep learning technologies in the healthcare domain. However, to safely and practically deploy deep lear…