activity
20172022
most citedSteganoGAN: High Capacity Image Steganography with GANs

78 citations · 121 across the 9 of their papers we have counts for

collaborators

20 papers

cs.LG202221 cited

Sintel: A Machine Learning Framework to Extract Insights from Signals

Sarah Alnegheimish, Dongyu Liu, Carles Sala +2

The detection of anomalies in time series data is a critical task with many monitoring applications. Existing systems often fail to encompass an end-to-end detection process, to fa…

cs.LG20224 cited

The Need for Interpretable Features: Motivation and Taxonomy

Alexandra Zytek, Ignacio Arnaldo, Dongyu Liu +2

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their…

cs.HC20212 cited

VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models

Furui Cheng, Dongyu Liu, Fan Du +5

Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks. Although many ML models perform promisingly, issues with model…

cs.HC2021

Meeting in the notebook: a notebook-based environment for micro-submissions in data science collaborations

Micah J. Smith, Jürgen Cito, Kalyan Veeramachaneni

Developers in data science and other domains frequently use computational notebooks to create exploratory analyses and prototype models. However, they often struggle to incorporate…

cs.HC20216 cited

AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data

Dongyu Liu, Kalyan Veeramachaneni, Alexander Geiger +2

Anomaly detection plays a key role in air quality analysis by enhancing situational awareness and alerting users to potential hazards. However, existing anomaly detection approache…

cs.HC2021

Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making

Alexandra Zytek, Dongyu Liu, Rhema Vaithianathan +1

Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked t…