Abstract
When building a classifier in interactive machine learning (iML), human knowledge about the target class can be a powerful reference to make the classifier robust to unseen items. The main challenge lies in finding unlabeled items that can either help discover or refine concepts for which the current classifier has no corresponding features (i.e., it has feature blindness). Yet it is unrealistic to ask humans to come up with an exhaustive list of items, especially for rare concepts that are hard to recall. This article presents AnchorViz, an interactive visualization that facilitates the discovery of prediction errors and previously unseen concepts through human-driven semantic data exploration. By creating example-based or dictionary-based anchors representing concepts, users create a topology that (a) spreads data based on their similarity to the concepts and (b) surfaces the prediction and label inconsistencies between data points that are semantically related. Once such inconsistencies and errors are discovered, users can encode the new information as labels or features and interact with the retrained classifier to validate their actions in an iterative loop. We evaluated AnchorViz through two user studies. Our results show that AnchorViz helps users discover more prediction errors than stratified random and uncertainty sampling methods. Furthermore, during the beginning stages of a training task, an iML tool with AnchorViz can help users build classifiers comparable to the ones built with the same tool with uncertainty sampling and keyword search, but with fewer labels and more generalizable features. We discuss exploration strategies observed during the two studies and how AnchorViz supports discovering, labeling, and refining of concepts through a sensemaking loop.
- Charu C. Aggarwal and ChengXiang Zhai. 2012. Mining Text Data. Springer Science 8 Business Media. Google ScholarDigital Library
- Jae-wook Ahn and Peter Brusilovsky. 2009. Adaptive visualization of search results: Bringing user models to visual analytics. Information Visualization 8, 3 (2009), 167--179. Google ScholarDigital Library
- Saleema Amershi, Maya Cakmak, William Bradley Knox, and Todd Kulesza. 2014. Power to the people: The role of humans in interactive machine learning. AI Magazine 35, 4 (2014), 105--120.Google ScholarDigital Library
- Saleema Amershi, Max Chickering, Steven M. Drucker, Bongshin Lee, Patrice Simard, and Jina Suh. 2015. Modeltracker: Redesigning performance analysis tools for machine learning. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. ACM, 337--346. Google ScholarDigital Library
- Saleema Amershi, James Fogarty, and Daniel Weld. 2012. Regroup: Interactive machine learning for on-demand group creation in social networks. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 21--30. Google ScholarDigital Library
- Joshua Attenberg, Panos Ipeirotis, and Foster Provost. 2015. Beat the machine: Challenging humans to find a predictive model’s “unknown unknowns”. Journal of Data and Information Quality (JDIQ) 6, 1 (2015), 1. Google ScholarDigital Library
- Josh Attenberg and Foster Provost. 2010. Why label when you can search?: Alternatives to active learning for applying human resources to build classification models under extreme class imbalance. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 423--432. Google ScholarDigital Library
- Michael Brooks, Saleema Amershi, Bongshin Lee, Steven M. Drucker, Ashish Kapoor, and Patrice Simard. 2015. FeatureInsight: Visual support for error-driven feature ideation in text classification. In Proceedings of the IEEE Conference on Visual Analytics Science and Technology (VAST’15). IEEE, 105--112.Google ScholarCross Ref
- Mackinlay Card. 1999. Readings in Information Visualization: Using Vision to Think. Morgan-Kaufmann. Google ScholarDigital Library
- Duen Horng Chau, Aniket Kittur, Jason I. Hong, and Christos Faloutsos. 2011. Apolo: Making sense of large network data by combining rich user interaction and machine learning. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 167--176. Google ScholarDigital Library
- Nan-Chen Chen, Jina Suh, Johan Verwey, Gonzalo Ramos, Steven Drucker, and Patrice Simard. 2018. AnchorViz: Facilitating classifier error discovery through interactive semantic data exploration. In Proceedings of the 23rd International Conference on Intelligent User Interfaces. ACM, 269--280. Google ScholarDigital Library
- Justin Cheng and Michael S. Bernstein. 2015. Flock: Hybrid crowd-machine learning classifiers. In Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work 8 Social Computing. ACM, 600--611. Google ScholarDigital Library
- Jason Chuang, Sonal Gupta, Christopher Manning, and Jeffrey Heer. 2013. Topic model diagnostics: Assessing domain relevance via topical alignment. In Proceedings of the International Conference on Machine Learning. 612--620. Google ScholarDigital Library
- Aron Culotta, Trausti Kristjansson, Andrew McCallum, and Paul Viola. 2006. Corrective feedback and persistent learning for information extraction. Artificial Intelligence 170, 14–15 (2006), 1101--1122. Google ScholarDigital Library
- Pedro Domingos. 2012. A few useful things to know about machine learning. Commun. ACM 55, 10 (2012), 78--87. Google ScholarDigital Library
- A. Endert, W. Ribarsky, C. Turkay, B. L. Wong, Ian Nabney, I. Díaz Blanco, and F. Rossi. 2017. The state of the art in integrating machine learning into visual analytics. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 458--486.Google Scholar
- Jerry Alan Fails and Dan R. Olsen, Jr. 2003. Interactive machine learning. In Proceedings of the 8th International Conference on Intelligent User Interfaces (IUI’03). ACM, New York, 39--45.Google Scholar
- James Fogarty, Desney Tan, Ashish Kapoor, and Simon Winder. 2008. CueFlik: Interactive concept learning in image search. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 29--38. Google ScholarDigital Library
- Thomas M. J. Fruchterman and Edward M. Reingold. 1991. Graph drawing by force-directed placement. Software: Practice and Experience 21, 11 (1991), 1129--1164. Google ScholarDigital Library
- Björn Hartmann, Leith Abdulla, Manas Mittal, and Scott R. Klemmer. 2007. Authoring sensor-based interactions by demonstration with direct manipulation and pattern recognition. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 145--154. Google ScholarDigital Library
- Florian Heimerl, Charles Jochim, Steffen Koch, and Thomas Ertl. 2012. FeatureForge: A novel tool for visually supported feature engineering and corpus revision. In COLING.Google Scholar
- Patrick E Hoffman. {n.d.}. Table Visualizations: A Formal Model and Its Applications. Ph.D. Dissertation. University of Massachusetts. Lowell. Google ScholarDigital Library
- Rong Hu, Sarah Jane Delany, and Brian Mac Namee. 2010. EGAL: Exploration guided active learning for TCBR. In Proceedings of the International Conference on Case-Based Reasoning. Springer, 156--170. Google ScholarDigital Library
- Xinran Hu, Lauren Bradel, Dipayan Maiti, Leanna House, and Chris North. 2013. Semantics of directly manipulating spatializations. IEEE Transactions on Visualization and Computer Graphics 19, 12 (2013), 2052--2059. Google ScholarDigital Library
- Camille Jandot, Patrice Simard, Max Chickering, David Grangier, and Jina Suh. 2016. Interactive semantic featuring for text classification. arXiv preprint arXiv:1606.07545 (2016).Google Scholar
- Ian Jolliffe. 2011. Principal component analysis. In International Encyclopedia of Statistical Science. Springer, 1094--1096.Google Scholar
- Hannah Kim, Jaegul Choo, Haesun Park, and Alex Endert. 2016. InterAxis: Steering scatterplot axes via observation-level interaction. IEEE Transactions on Visualization and Computer Graphics 22, 1 (2016), 131--140.Google ScholarDigital Library
- Josua Krause, Adam Perer, and Enrico Bertini. 2014. INFUSE: Interactive feature selection for predictive modeling of high dimensional data. IEEE Transactions on Visualization and Computer Graphics 20, 12 (2014), 1614--1623.Google ScholarCross Ref
- Josua Walter Hugo Krause. 2018. Using Visual Analytics to Explain Black-Box Machine Learning. Ph.D. Dissertation. New York University Tandon School of Engineering.Google Scholar
- Todd Kulesza, Saleema Amershi, Rich Caruana, Danyel Fisher, and Denis Charles. 2014. Structured labeling for facilitating concept evolution in machine learning. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 3075--3084. Google ScholarDigital Library
- Todd Kulesza, Simone Stumpf, Weng-Keen Wong, Margaret M. Burnett, Stephen Perona, Andrew Ko, and Ian Oberst. 2011. Why-oriented end-user debugging of naive Bayes text classification. ACM Transactions on Interactive Intelligent Systems (TiiS) 1, 1 (2011), 2. Google ScholarDigital Library
- Himabindu Lakkaraju, Ece Kamar, Rich Caruana, and Eric Horvitz. 2017. Identifying unknown unknowns in the open world: Representations and policies for guided exploration. In Proceedings of AAAI. 2124--2132. Google ScholarDigital Library
- Ken Lang. 1995. Newsweeder: Learning to filter netnews. In Proceedings of the 12th International Conference on Machine Learning, Vol. 10. 331--339. Google ScholarDigital Library
- Hanseung Lee, Jaeyeon Kihm, Jaegul Choo, John Stasko, and Haesun Park. 2012. iVisClustering: An interactive visual document clustering via topic modeling. Computer Graphics Forum 31, 3pt3 (June 2012), 1155--1164. 00041 Google ScholarDigital Library
- David D. Lewis and Jason Catlett. 1994. Heterogeneous uncertainty sampling for supervised learning. In Proceedings of the 11th International Conference on Machine Learning. 148--156. Google ScholarDigital Library
- David D. Lewis and William A. Gale. 1994. A sequential algorithm for training text classifiers. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Springer-Verlag New York, Inc., 3--12. Google Scholar
- Shusen Liu, Dan Maljovec, Bei Wang, Peer-Timo Bremer, and Valerio Pascucci. 2015. Visualizing high-dimensional data: Advances in the past decade. IEEE Transactions on Visualization and Computer Graphics 23, 3 (2017), 1249–1268. Google ScholarDigital Library
- Shixia Liu, Xiting Wang, Mengchen Liu, and Jun Zhu. 2017. Towards better analysis of machine learning models: A visual analytics perspective. Visual Informatics 1, 1 (2017), 48--56.Google ScholarCross Ref
- Shixia Liu, Jiannan Xiao, Junlin Liu, Xiting Wang, Jing Wu, and Jun Zhu. 2018. Visual diagnosis of tree boosting methods. IEEE Transactions on Visualization 8 Computer Graphics 1 (2018), 1--1.Google ScholarDigital Library
- Yafeng Lu, Rolando Garcia, Brett Hansen, Michael Gleicher, and Ross Maciejewski. 2017. The state-of-the-art in predictive visual analytics. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 539--562. Google ScholarDigital Library
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, Nov (2008), 2579--2605.Google Scholar
- Brian Mac Namee, Rong Hu, and Sarah Jane Delany. 2010. Inside the selection box: Visualising active learning selection strategies. In Proceedings of The Challenges of Data Visualization Neural Information Processing Systems (NIPS) Workshop. Dublin Institute of Technology.Google Scholar
- Christopher D. Manning and Hinrich Schütze. 1999. Foundations of Statistical Natural Language Processing. MIT Press. Google ScholarDigital Library
- Christopher Meek. 2016. A characterization of prediction errors. CoRR abs/1611.05955 (2016). http://arxiv.org/abs/1611.05955Google Scholar
- Gregory Murphy. 2004. The Big Book of Concepts. MIT Press.Google Scholar
- R. M. Nosofsky. 1986. Attention, similarity, and the identification-categorization relationship. Journal of Experimental Psychology. General 115 1 (1986), 39--61.Google Scholar
- Kai A. Olsen, James G. Williams, Kenneth M. Sochats, and Stephen C. Hirtle. 1992. Ideation through visualization: The VIBE system. Multimedia Review 3 (1992), 48--48.Google Scholar
- Peter Pirolli and Stuart Card. 2005. The sensemaking process and leverage points for analyst technology as identified through cognitive task analysis. In Proceedings of the International Conference on Intelligence Analysis, Vol. 5. 2--4.Google Scholar
- Hema Raghavan, Omid Madani, and Rosie Jones. 2005. InterActive feature selection. In Proceedings of IJCAI, Vol. 5. 841--846. Google ScholarDigital Library
- D. Ren, S. Amershi, B. Lee, J. Suh, and J. D. Williams. 2017. Squares: Supporting interactive performance analysis for multiclass classifiers. IEEE Transactions on Visualization and Computer Graphics 23, 1 (Jan. 2017), 61--70. 00000. Google ScholarDigital Library
- Eleanor Rosch and Carolyn B. Mervis. 1975. Family resemblances: Studies in the internal structure of categories. Cognitive Psychology 7, 4 (1975), 573--605.Google ScholarCross Ref
- Daniel M. Russell, Mark J. Stefik, Peter Pirolli, and Stuart K. Card. 1993. The cost structure of sensemaking. In Proceedings of the INTERACT’93 and CHI’93 Conference on Human Factors in Computing Systems (CHI’93). ACM, New York, 269--276. Google ScholarDigital Library
- John W. Sammon. 1969. A nonlinear mapping for data structure analysis. IEEE Transactions on Computers 100, 5 (1969), 401--409. Google ScholarDigital Library
- Sam Scott and Stan Matwin. 1999. Feature engineering for text classification. In Proceedings of ICML, Vol. 99. 379--388. Google ScholarDigital Library
- Burr Settles. 2011. Closing the loop: Fast, interactive semi-supervised annotation with queries on features and instances. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1467--1478. Google ScholarDigital Library
- Burr Settles. 2012. Active learning. Synthesis Lectures on Artificial Intelligence and Machine Learning 6, 1 (2012), 1--114. Google ScholarDigital Library
- John Sharko, Georges Grinstein, and Kenneth A Marx. 2008. Vectorized radviz and its application to multiple cluster datasets. IEEE Transactions on Visualization and Computer Graphics 14, 6 (2008). Google ScholarDigital Library
- Ben Shneiderman. 1992. Tree visualization with tree-maps: 2-d space-filling approach. ACM Trans. Graph. 11, 1 (Jan. 1992), 92--99. Google ScholarDigital Library
- Edward E. Smith and Douglas L. Medin. 1981. Categories and Concepts. Vol. 9. Harvard University Press, Cambridge, MA.Google Scholar
- Robert R. Sokal. 1958. A statistical method for evaluating systematic relationship. University of Kansas Science Bulletin 28 (1958), 1409--1438.Google Scholar
- Ji Soo Yi, Rachel Melton, John Stasko, and Julie A. Jacko. 2005. Dust 8 magnet: Multivariate information visualization using a magnet metaphor. Information Visualization 4, 4 (2005), 239--256. Google ScholarDigital Library
- Simone Stumpf, Vidya Rajaram, Lida Li, Weng-Keen Wong, Margaret Burnett, Thomas Dietterich, Erin Sullivan, and Jonathan Herlocker. 2009. Interacting meaningfully with machine learning systems: Three experiments. International Journal of Human-Computer Studies 67, 8 (2009), 639--662. Google ScholarDigital Library
- Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, and Manfred Stede. 2011. Lexicon-based methods for sentiment analysis. Computational Linguistics 37, 2 (2011), 267--307. Google ScholarDigital Library
- Justin Talbot, Bongshin Lee, Ashish Kapoor, and Desney S. Tan. 2009. EnsembleMatrix: Interactive visualization to support machine learning with multiple classifiers. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI’09). ACM, New York, 1283--1292. 00097. Google ScholarDigital Library
- Stef Van Den Elzen and Jarke J van Wijk. 2011. Baobabview: Interactive construction and analysis of decision trees. In Proceedings of the IEEE Conference on Visual Analytics Science and Technology (VAST’11). IEEE, 151--160.Google ScholarCross Ref
- Alfredo Vellido Alcacena, José David Martín, Fabrice Rossi, and Paulo J. G. Lisboa. 2011. Seeing is believing: The importance of visualization in real-world machine learning applications. In Proceedings of the 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011: Bruges, Belgium, April 27-28-29, 2011. 219--226.Google Scholar
- Byron C. Wallace, Kevin Small, Carla E. Brodley, Joseph Lau, and Thomas A. Trikalinos. 2012. Deploying an interactive machine learning system in an evidence-based practice center: abstrackr. In Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium. ACM, 819--824. Google ScholarDigital Library
- Malcolm Ware, Eibe Frank, Geoffrey Holmes, Mark Hall, and Ian H. Witten. 2001. Interactive machine learning: Letting users build classifiers. International Journal of Human-Computer Studies 55, 3 (2001), 281--292. Google ScholarDigital Library
- Yiming Yang and Jan O. Pedersen. 1997. A comparative study on feature selection in text categorization. In ICML, Vol. 97. 412--420. Google ScholarDigital Library
- J. Zhang, Y. Wang, P. Molino, L. Li, and D. S. Ebert. 2018. Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models. IEEE Transactions on Visualization and Computer Graphics (2018).Google Scholar
Index Terms
- AnchorViz: Facilitating Semantic Data Exploration and Concept Discovery for Interactive Machine Learning
Recommendations
AnchorViz: Facilitating Classifier Error Discovery through Interactive Semantic Data Exploration
IUI '18: Proceedings of the 23rd International Conference on Intelligent User InterfacesWhen building a classifier in interactive machine learning, human knowledge about the target class can be a powerful reference to make the classifier robust to unseen items. The main challenge lies in finding unlabeled items that can either help discover ...
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
Learning Instance Weighted Naive Bayes from labeled and unlabeled data
In real-world data mining applications, it is often the case that unlabeled instances are abundant, while available labeled instances are very limited. Thus, semi-supervised learning, which attempts to benefit from large amount of unlabeled data ...
Comments