Xin Qian
Fan Du
ABSTRACT
Visualization recommendation is important for exploratory analysis and making sense of the data quickly by automatically recommending relevant visualizations to the user. In this work, we propose the first end-to-end ML-based visualization recommendation system that leverages a large corpus of datasets and their relevant visualizations to learn a visualization recommendation model automatically. Then, given a new unseen dataset from an arbitrary user, the model automatically generates visualizations for that new dataset, derives scores for the visualizations, and outputs a list of recommended visualizations to the user ordered by effectiveness. We also describe an evaluation framework to quantitatively evaluate visualization recommendation models learned from a large corpus of visualizations and datasets. Through quantitative experiments, a user study, and qualitative analysis, we show that our end-to-end ML-based system recommends more effective and useful visualizations compared to existing state-of-the-art rule-based systems.
Supplemental Material
- Gediminas Adomavicius and Alexander Tuzhilin. 2005. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. TKDE , Vol. 17, 6 (2005), 734--749.Google Scholar
Digital Library
- Anushka Anand and Justin Talbot. 2015. Automatic selection of partitioning variables for small multiple displays. TVCG , Vol. 22, 1 (2015), 669--677.Google ScholarDigital Library
- James Bennett, Stan Lanning, et almbox. 2007. The netflix prize. In KDD Cup. 35.Google Scholar
- Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, et almbox. 2016. Wide & deep learning for recommender systems. In Workshop on Deep Learning for Recommender Systems. 7--10.Google ScholarDigital Library
- Tuan Nhon Dang and Leland Wilkinson. 2014. Scagexplorer: Exploring scatterplots by their scagnostics. In IEEE Pacific visualization symposium .Google Scholar
- Cagatay Demiralp, Peter J Haas, Srinivasan Parthasarathy, and Tejaswini Pedapati. 2017. Foresight: Recommending Visual Insights. VLDB Endowment (2017).Google Scholar
- Mark Derthick, John Kolojejchick, and Steven F Roth. 1997. An interactive visualization environment for data exploration. In KDD. 2--9.Google Scholar
- Victor Dibia and cC aug atay Demiralp. 2019. Data2vis: Automatic generation of data visualizations using sequence-to-sequence recurrent neural networks. IEEE computer graphics and applications , Vol. 39, 5 (2019), 33--46.Google Scholar
- Humaira Ehsan, Mohamed Sharaf, and Panos Chrysanthis. 2016. Muve: Efficient multi-objective view recommendation for visual data exploration. In ICDE .Google Scholar
- David Gotz and Zhen Wen. 2009. Behavior-driven visualization recommendation. In IUI. 315--324.Google Scholar
- Camille Harris, Ryan A Rossi, Sana Malik, Jane Hoffswell, Fan Du, Tak Yeon Lee, Eunyee Koh, and Handong Zhao. 2021. Insight-centric Visualization Recommendation. arXiv:2103.11297 (2021).Google Scholar
- Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In SIGIR. 355--364.Google Scholar
- Jeffrey Heer, Nicholas Kong, and Maneesh Agrawala. 2009. Sizing the horizon: the effects of chart size and layering on the graphical perception of time series visualizations. In CHI. 1303--1312.Google Scholar
- Kevin Hu, Michiel Bakker, Stephen Li, Tim Kraska, and César Hidalgo. 2019. Vizml: A machine learning approach to visualization recommendation. In CHI .Google ScholarDigital Library
- Kevin Hu, Diana Orghian, and César Hidalgo. 2018. Dive: A mixed-initiative system supporting integrated data exploration workflows. In Workshop on Human-In-the-Loop Data Anal. 1--7.Google ScholarDigital Library
- Kalervo J"arvelin and Jaana Kek"al"ainen. 2002. Cumulated gain-based evaluation of IR techniques. TOIS , Vol. 20, 4 (2002), 422--446.Google Scholar
- Younghoon Kim and Jeffrey Heer. 2018. Assessing Effects of Task and Data Distribution on the Effectiveness of Visual Encodings. EuroVis (2018).Google Scholar
- Doris Jung-Lin Lee. 2020. Insight Machines: The Past, Present, and Future of Visualization Recommendation .Google Scholar
- Doris Jung-Lin Lee, Himel Dev, Huizi Hu, Hazem Elmeleegy, and Aditya Parameswaran. 2019 a. Avoiding drill-down fallacies with VisPilot: assisted exploration of data subsets. In IUI . 186--196.Google Scholar
- Doris Jung-Lin Lee, John Lee, Tarique Siddiqui, Jaewoo Kim, Karrie Karahalios, and Aditya Parameswaran. 2019 b. You can't always sketch what you want: Understanding Sensemaking in Visual Query Systems. TVCG , Vol. 26, 1 (2019), 1267--1277.Google Scholar
- Halden Lin, Dominik Moritz, and Jeffrey Heer. 2020. Dziban: Balancing Agency & Automation in Visualization Design via Anchored Recommendations. In CHI .Google Scholar
- Greg Linden, Brent Smith, and Jeremy York. 2003. Amazon.com recommendations: Item-to-item collaborative filtering. Internet Computing , Vol. 7, 1 (2003), 76--80.Google ScholarDigital Library
- Yang Liu and Jeffrey Heer. 2018. Somewhere over the rainbow: An empirical assessment of quantitative colormaps. In CHI . 1--12.Google Scholar
- Jock Mackinlay. 1986. Automating the design of graphical presentations of relational information. ACM Trans. Graph. , Vol. 5, 2 (1986), 110--141.Google ScholarDigital Library
- Jock Mackinlay, Pat Hanrahan, and Chris Stolte. 2007. Show Me: Automatic presentation for visual analysis. TVCG , Vol. 13, 6 (2007), 1137--1144.Google ScholarDigital Library
- Dominik Moritz, Chenglong Wang, Greg L Nelson, Halden Lin, Adam M Smith, Bill Howe, and Jeffrey Heer. 2018. Formalizing visualization design knowledge as constraints: Actionable and extensible models in draco. TVCG , Vol. 25, 1 (2018).Google ScholarCross Ref
- Michael Oppermann, Robert Kincaid, and Tamara Munzner. 2021. VizCommender: Computing Text-Based Similarity in Visualization Repositories for Content-Based Recommendations. TVCG , Vol. 27, 02 (2021), 495--505.Google ScholarCross Ref
- Daniel B Perry, Bill Howe, Alicia MF Key, and Cecilia Aragon. 2013. VizDeck: Streamlining exploratory visual analytics of scientific data. In iConference .Google Scholar
- Xin Qian, Ryan A Rossi, Fan Du, Sungchul Kim, Eunyee Koh, Sana Malik, Tak Yeon Lee, and Nesreen K Ahmed. 2021. Personalized Visualization Recommendation. arXiv:2102.06343 (2021).Google Scholar
- Xin Qian, Ryan A Rossi, Fan Du, Sungchul Kim, Eunyee Koh, Sana Malik, Tak Yeon Lee, and Joel Chan. 2020. ML-based Visualization Recommendation: Learning to Recommend Visualizations from Data. arXiv:2009.12316 (2020).Google Scholar
- Steven F Roth, John Kolojejchick, Joe Mattis, and Jade Goldstein. 1994. Interactive graphic design using automatic presentation knowledge. In CHI . 112--117.Google Scholar
- Bahador Saket, Alex Endert, and cC aug atay Demiralp. 2018. Task-based effectiveness of basic visualizations. TVCG , Vol. 25, 7 (2018), 2505--2512.Google ScholarCross Ref
- Sunita Sarawagi, Rakesh Agrawal, and Nimrod Megiddo. 1998. Discovery-driven exploration of OLAP data cubes. In Extending Database Tech. 168--182.Google Scholar
- Marc M. Sebrechts, John V. Cugini, Sharon J. Laskowski, Joanna Vasilakis, and Michael S. Miller. 1999. Visualization of Search Results: A Comparative Evaluation of Text, 2D, and 3D Interfaces. In SIGIR .Google Scholar
- Tarique Siddiqui, Albert Kim, John Lee, Karrie Karahalios, and Aditya Parameswaran. 2016. Effortless Data Exploration with zenvisage: An Expressive and Interactive Visual Analytics System. VLDB Endowment (2016).Google ScholarDigital Library
- Chris Stolte, Diane Tang, and Pat Hanrahan. 2002. Polaris: A system for query, analysis, and visualization of multidimensional relational databases. TVCG , Vol. 8, 1 (2002), 52--65.Google ScholarDigital Library
- Manasi Vartak, Silu Huang, Tarique Siddiqui, Samuel Madden, and Aditya Parameswaran. 2017. Towards visualization recommendation systems. SIGMOD , Vol. 45, 4 (2017), 34--39.Google ScholarDigital Library
- Manasi Vartak, Sajjadur Rahman, Samuel Madden, Aditya Parameswaran, and Neoklis Polyzotis. 2015. SeeDB: Efficient Data-Driven Visualization Recommendations to Support Visual Analytics. (2015).Google Scholar
- Leland Wilkinson, Anushka Anand, and Robert Grossman. 2005. Graph-theoretic scagnostics. In IEEE Symposium on Information Visualization . 157--164.Google Scholar
- Graham Wills and Leland Wilkinson. 2010. Autovis: automatic visualization. Information Visualization , Vol. 9, 1 (2010), 47--69.Google ScholarDigital Library
- Kanit Wongsuphasawat, Dominik Moritz, Anushka Anand, Jock Mackinlay, Bill Howe, and Jeffrey Heer. 2015. Voyager: Exploratory analysis via faceted browsing of visualization recommendations. TVCG , Vol. 22, 1 (2015), 649--658.Google ScholarDigital Library
- Kanit Wongsuphasawat, Dominik Moritz, Anushka Anand, Jock Mackinlay, Bill Howe, and Jeffrey Heer. 2016. Towards a general-purpose query language for visualization recommendation. In Workshop on Human-In-the-Loop Data Anal.Google ScholarDigital Library
- Kanit Wongsuphasawat, Zening Qu, Dominik Moritz, Riley Chang, Felix Ouk, Anushka Anand, Jock Mackinlay, Bill Howe, and Jeffrey Heer. 2017. Voyager 2: Augmenting visual analysis with partial view specifications. In CHI . 2648--2659.Google Scholar
- Aoyu Wu, Liwenhan Xie, Bongshin Lee, Yun Wang, Weiwei Cui, and Huamin Qu. 2021. Learning to Automate Chart Layout Configurations Using Crowdsourced Paired Comparison. In CHI .Google Scholar
Index Terms
- Learning to Recommend Visualizations from Data
Recommendations
Visualizing Visualizations: User Interfaces for Managing and Exploring Scientific Visualization Data
The process of scientific visualization is inherently iterative. A good visualization comes from experimenting with visualization, rendering, and viewing parameters to bring out the most relevant information in the data. A good data visualization system ...
Constructing Interactive Visualizations with iVoLVER
CHI EA '16: Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing SystemsiVoLVER, the Interactive Visual Language for Visualization Extraction and Reconstruction, is a web-based pen and touch system that graphically supports the construction of interactive visualizations and allows the extraction of data from different types ...
Comments