CS 8395-03 - Visual Analytics & Machine Learning
Papers
Note: you may choose those papers annotated with (*) for presentation, please see syllabus for more details.
Survey Papers
Start here, before getting in to the details of the papers below.
- Visual Analytics: Definition, Process and Challenges
- What you see is what you can change: Human-centered machine learning by interactive visualization
- Power to the People: The Role of Humans in Interactive Machine Learning
- The State of the Art in Integrating Machine Learning into Visual Analytics
- The State-of-the-Art in Predictive Visual Analytics
- Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers
Mixed-Initiative Visual Exploration
- ParallelTopics: A Probabilistic Approach to Exploring Document Collections
- TopicPanorama: a Full Picture of Relevant Topics
- Comparative Exploration of Document Collections: a Visual Analytics Approach
- VAiRoma: A Visual Analytics System for Making Sense of Places, Times, and Events in Roman History
- Serendip: Topic Model-Driven Visual Exploration of Text Corpora
- AxiSketcher: Interactive Nonlinear Axis Mapping ofVisualizations through User Drawings
- Podium: Ranking Data Using Mixed-Initiative Visual Analytics
- Knowledge-Assisted Ranking: A Visual Analytic Application for Sports Event Data
- NEREx: Named-Entity Relationship Explorationin Multi-Party Conversations
- ConToVi: Multi-Party Conversation Exploration using Topic-Space Views
- Steerable, Progressive Multidimensional Scaling
- A Visual Interaction Framework for Dimensionality Reduction Based Data Exploration
- iPCA: An Interactive System for PCA-based Visual Analytics
- Visual cluster analysis of trajectory data with interactive Kohonen maps
- Supporting Analysis of Dimensionality Reduction Results with Contrastive Learning
- SAX Navigator: Time Series Exploration through Hierarchical Clustering
- Brushing Dimensions – A Dual Visual Analysis Model for High-dimensional Data
- Semantics of Directly Manipulating Spatializations
- Representative Factor Generation for the Interactive Visual Analysis of High-Dimensional Data
- Designing Progressive and Interactive Analytics Processes for High-Dimensional Data Analysis
- Feedback-Driven Interactive Exploration of Large Multidimensional Data Supported by Visual Classifier
- cite2vec: Citation-Driven Document Exploration via Word Embeddings
- Approximated and User Steerable tSNE for Progressive Visual Analytics
- Interactive Visual Graph Mining and Learning
- HierarchicalTopics: Visually Exploring Large Text Collections Using Topic Hierarchies*
- Spatiotemporal Social Media Analytics for Abnormal Event Detection and Examination using Seasonal-Trend Decomposition*
- ThemeDelta: Dynamic Segmentations over Temporal Topic Models*
- PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models*
- InterAxis: Steering Scatterplot Axes via Observation-Level Interaction*
- Clustervision: Visual Supervision of Unsupervised Clustering*
- Clustrophile 2: Guided Visual Clustering Analysis*
- ConceptVector: Text Visual Analytics via Interactive LexiconBuilding using Word Embedding*
- RegressionExplorer: Interactive Exploration of Logistic Regression Models with Subgroup Analysis*
- TopicSifter: Interactive Search Space Reduction Through Targeted Topic Modeling*
Visual Analytics for Understanding Models
- Squares: Supporting Interactive Performance Analysis for Multiclass Classifiers
- UnTangle Map: Visual Analysis of Probabilistic Multi-Label Data
- Visual Methods for Analyzing Probabilistic Classification Data
- EnsembleMatrix: Interactive Visualization to Support Machine Learning with Multiple Classifiers
- Towards Better Analysis of Deep Convolutional Neural Networks
- Do Convolutional Neural Networks Learn Class Hierarchy?
- LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
- Analyzing the Training Processes of Deep Generative Models
- GANViz: A Visual Analytics Approach to Understand the Adversarial Game
- GAN Lab: Understanding Complex Deep Generative Models usingInteractive Visual Experimentation
- EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
- Visual Exploration of Semantic Relationships in Neural Word Embeddings
- NLIZE: A Perturbation-Driven Visual Interrogation Tool for Analyzing and Interpreting Natural Language Inference Models
- Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow
- DeepTracker: Visualizing the Training Process of Convolutional Neural Networks
- RuleMatrix: Visualizing and Understanding Classifiers with Rules
- Visual Diagnosis of Tree Boosting Methods
- explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
- Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models*
- DeepEyes: Progressive Visual Analytics for Designing Deep Neural Networks*
- ACTIVIS: Visual Exploration of Industry-Scale Deep Neural Network Models*
- RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks*
- Understanding Hidden Memories of Recurrent Neural Networks*
- SEQ2SEQ-VIS: A Visual Debugging Tool for Sequence-to-Sequence Models*
- Interactive Analysis of Word Vector Embeddings*
- Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations*
- DQNViz: A Visual Analytics Approach to Understand Deep Q-Networks*
- The What-If Tool: Interactive Probing of Machine Learning Models*
- SUMMIT: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations*
Visual Analytics for Training Models
- An Analysis of Machine- and Human-Analytics in Classification
- iVisClassifier: An Interactive Visual Analytics System for Classification Based on Supervised Dimension Reduction
- Visual Classifier Training for Text Document Retrieval
- Inter-Active Learning of Ad-Hoc Classifiers for Video Visual Analytics
- Dis-Function: Learning Distance Functions Interactively
- Towards User-Centered Active Learning Algorithms
- Comparing Visual-Interactive Labeling with Active Learning: An Experimental Study
- Visual Supervision in Bootstrapped Information Extraction
- Visualization-Based Active Learning for Video Annotation
- VIAL – A Unified Process for Visual-Interactive Labeling
- Interactive Optimization for Steering Machine Classification
- Integrating Data and Model Space in Ensemble Learning by Visual Analytics
- The Exploratory Labeling Assistant: Mixed-Initiative Label Curation with Large Document Collections
- LTMA: Layered Topic Matching for the Comparative Exploration, Evaluation, and Refinement of Topic Modeling Results
- VIANA: Visual Interactive Annotation of Argumentation
- ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling
- Closing the Loop: User-Centered Design and Evaluation of a Human-in-the-Loop Topic Modeling System
- An Approach to Supporting Incremental Visual Data Classification
- AnchorViz: Facilitating Classifier Error Discovery through Interactive Semantic Data Exploration
- BEAMES: Interactive Multi-Model Steering, Selection, and Inspection for Regression Tasks
- Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures
- UTOPIAN: User-Driven Topic Modeling Based on Interactive Nonnegative Matrix Factorization*
- Progressive Learning of Topic Modeling Parameters: A Visual Analytics Framework*
- Visual Analytics for Topic Model Optimization based on User-Steerable Speculative Execution*
- BaobabView: Interactive construction and analysis of decision trees*
- ProtoSteer: Steering Deep Sequence Model with Prototypes*
- Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections*
Learning Visualization
- Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks
- DeepEye: Towards Automatic Data Visualization
- Formalizing Visualization Design Knowledge as Constraints: Actionable and Extensible Models in Draco
- Show Me: Automatic Presentation for Visual Analysis
- SEEDB: Efficient Data-Driven Visualization Recommendations to Support Visual Analytics
- Voyager 2: Augmenting Visual Analysis with Partial View Specifications
- Towards Visualization Recommendation Systems
- GraphScape: A Model for Automated Reasoning about Visualization Similarity and Sequencing
- VizML: A Machine Learning Approach to Visualization Recommendation
- Fast and Accurate CNN-based Brushing in Scatterplots
- FlowNet: A Deep Learning Framework for Clustering and Selection of Streamlines and Stream Surfaces
- A Generative Model for Volume Rendering
- What Would a Graph Look Like in This Layout? A Machine Learning Approach to Large Graph Visualization