DashBot: Insight-Driven Dashboard Generation Based on Deep Reinforcement Learning

@article{Deng2022DashBotID,
  title={DashBot: Insight-Driven Dashboard Generation Based on Deep Reinforcement Learning},
  author={Dazhen Deng and Aoyu Wu and Huamin Qu and Yingcai Wu},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  year={2022},
  volume={29},
  pages={690-700}
}
Analytical dashboards are popular in business intelligence to facilitate insight discovery with multiple charts. However, creating an effective dashboard is highly demanding, which requires users to have adequate data analysis background and be familiar with professional tools, such as Power BI. To create a dashboard, users have to configure charts by selecting data columns and exploring different chart combinations to optimize the communication of insights, which is trial-and-error. Recent… 
[PDF] Semantic Reader
5 Citations
Highly Influential Citations
1
Background Citations
1
Methods Citations
2

Figures and Tables from this paper

5 Citations

DMiner: Dashboard Design Mining and Recommendation

This work builds a new dataset containing 854 dashboards crawled online, develops feature engineering methods for describing the single views and view-wise relationships in terms of data, encoding, layout, and interactions, and identifies design rules among those features and develops a recommender for dashboard design.

Machine Learning for Visualization Recommendation Systems: Open Challenges and Future Directions

This paper aims to summarize the state-of-the-art of VRS, but also to outline promising future research directions.

KB4VA: A Knowledge Base of Visualization Designs for Visual Analytics

This work builds KB4VA, a knowledge base of visualization designs in VA systems with comprehensive labels about their analytical tasks and visual encodings, and extends Vega-Lite specifications for describing advanced and composited visualization Designs in a declarative manner, thus facilitating human understanding and automatic indexing.

Interactive Data Analysis with Next-step Natural Language Query Recommendation

A NLI with a step-wise query recommendation module to assist users in choosing appropriate next-step exploration actions and it is shown that this system can facilitate a more effective and systematic data analysis process than a baseline without the recommendation module.

MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization

This paper proposes MetaGlyph, an automatic system for generating MGVs from a spreadsheet that automatically selects metaphors with corresponding images from online resources based on the input data semantics and integrates a Monte Carlo tree search algorithm that explores the design of an MGV.

References

SHOWING 1-10 OF 82 REFERENCES

MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation

A deep-learning-based method that assists in designing analytical dashboards for analyzing a data table and integrates the deep learning models into a mixed-initiative system for visualization recommendation.

Automatically Generating Data Exploration Sessions Using Deep Reinforcement Learning

This work presents ATENA, a system that takes an input dataset and auto-generates a compelling exploratory session, presented in an EDA notebook, using a novel Deep Reinforcement Learning (DRL) architecture to effectively optimize the notebook generation.

PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning

This work proposes a reinforcement learning framework to train an AI agent that assists users in exploring the design space efficiently and generating well-optimized storylines and introduces PlotThread, an authoring tool that integrates a set of flexible interactions to support easy customization of storyline visualizations.

MobileVisFixer: Tailoring Web Visualizations for Mobile Phones Leveraging an Explainable Reinforcement Learning Framework

The proposed MobileVisFixer automates a mobile-friendly visualization re-design process with a novel reinforcement learning framework, and uses a greedy heuristic based on Policy Gradient methods to find solutions to this difficult, multi-criteria optimization problem in reasonable time.

VizML: A Machine Learning Approach to Visualization Recommendation

A novel machine learning-based approach to visualization recommendation that learns visualization design choices from a large corpus of datasets and associated visualizations that is comparable to human performance when predicting consensus visualization type and exceeds that of other visualization recommender systems.

Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks

Data2Vis is introduced, an end-to-end trainable neural translation model for automatically generating visualizations from given datasets that are comparable to manually created visualizations in a fraction of the time, with potential to learn more complex visualization strategies at scale.

Continuous control with deep reinforcement learning

This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.

Natural Language to Visualization by Neural Machine Translation

Supporting the translation from natural language (NL) query to visualization (NL2VIS) can simplify the creation of data visualizations because if successful, anyone can generate visualizations by…

Table2Charts: Learning Shared Representations for Recommending Charts on Multi-dimensional Data

This paper proposes Table2Charts framework which learns common patterns from a large corpus of (table, charts) pairs based on deep Q-learning with copying mechanism and heuristic searching, and does table-to-sequence generation, where each sequence follows a chart template.

Playing Atari with Deep Reinforcement Learning

This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
...