
I characterize my research as Human-Centered Data Science where I combine techniques from statistics, machine learning, and interactive data visualization to empower data scientists throughout their analytical workflow.
My current research focuses around several themes:
1. Designing tools for Interactive and Visual Data Science2. Providing insights with Interpretable Machine Learning
3. Innovating data science techniques for Data-Driven Healthcare
Adam Perer is an Assistant Research Professor at Carnegie Mellon University, where he is a member of the Human-Computer Interaction Institute and he co-leads the Data Interaction Group. His research integrates data visualization and machine learning techniques to create visual interactive systems to help users make sense out of big data. Lately, his research focuses on human-centered data science and extracting insights from clinical data to support data-driven medicine. This work has been published at premier venues in visualization, human-computer interaction, and medical informatics. He was previously a Research Scientist at IBM Research. He holds a Ph.D. in Computer Science from the University of Maryland, College Park.
Selected Publications
Regularizing Black-box Models for Improved Interpretability
Designing Alternative Representations of Confusion Matrices to Support Non-Expert Public Understanding of Algorithm Performance
Getting Playful with Explainable AI: Games with a Purpose to Improve Human Understanding of AI
Confronting data sparsity to identify potential sources of Zika virus spillover infection among primates
SearchLens: Composing and Capturing Complex User Interests for Exploratory Search
Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures
MAST: A Tool for Visualizing CNN Model Architecture Searches
The Human User in Progressive Visual Analytics
A User Study on the Effect of Aggregating Explanations for Interpreting Machine Learning Models
Seq2Seq-VIS : A Visual Debugging Tool for Sequence-to-Sequence Models
Clustervision: Visual Supervision of Unsupervised Clustering
Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models
Mining and exploring care pathways from electronic medical records with visual analytics
Data Driven Analytics for Personalized Healthcare
Supporting Iterative Cohort Construction with Visual Temporal Queries
Progressive Visual Analytics: User-Driven Visual Exploration of In-Progress Analytics
Orion: A System for Modeling, Transformation and Visualization of Multi-dimensional Heterogeneous Networks
INFUSE: Interactive Feature Selection for Predictive Modeling of High Dimensional Data
Predicting changes in hypertension control using electronic health records from a chronic disease management program
Frequence: Interactive Mining and Visualization of Temporal Frequent Event Sequences
A Methodology for Interactive Mining and Visual Analysis of Clinical Event Patterns using Electronic Health Record Data
Iterative cohort analysis and exploration
The Longitudinal Use of SaNDVis: Visual Social Network Analytics in the Enterprise
Data-Driven Exploration of Care Plans for Patients
MatrixFlow: Temporal Network Visual Analytics to Track Symptom Evolution during Disease Progression
Diversity among Enterprise Online Communities: Collaborating, Teaming, and Innovating through Social Media
Do You Want to Know? Recommending Strangers in the Enterprise
Visual Social Network Analytics for Relationship Discovery in the Enterprise
Orion: A System for Modeling, Transformation and Visualization of Multi-dimensional Heterogeneous Networks
Guess Who? Enriching the Social Graph through a Crowdsourcing Game
Integrating Querying and Browsing in Partial Graph Visualizations
Digital Traces of Interest: Deriving Interest Relationships from Social Media Interactions
Same Places, Same Things, Same People? Mining User Similarity on Social Media
Finding Beautiful Insights in the Chaos of Social Network Visualizations
Integrating Statistics and Visualization for Exploratory Power: From Long-Term Case Studies to Design Guidelines
Analyzing (Social Media) Networks with NodeXL
Search, Show Context, Expand on Demand: Supporting Large Graph Exploration with Degree-of-Interest
Systematic Yet Flexible Discovery: Guiding Domain Experts Through Exploratory Data Analysis
Integrating Statistics and Visualization: Case Studies of Gaining Clarity During Exploratory Data Analysis
Balancing Systematic and Flexible Exploration of Social Networks
Using rhythms of relationships to understand e-mail archives
Contrasting portraits of email practices: visual approaches to reflection and analysis
Teaching
- Interactive Data Science Spring 2021
- Interactive Data Science Fall 2020
- Data Science and Visualization Spring 2019
- Interpretable Machine Learning Spring 2019
Advising
-
PhD Students
- Alex Cabrera
- Sachin Grover
- Venkat Sivaraman
- Will Epperson
- Marius Hogräfer
- Youli Chang
- Aditi Dhabalia
- Andy Wilbourn
- Zhirou (Jenny) Xin
- Monica Chang
- Zhendong (Mike) Yuan
- Abraham Druck
- Kazi Jawad
Visiting PhD Students
Masters Students
Undergraduate Students