iCaseViz: Learning Case Similarities through Interaction with a Case Base Visualizer

Since the principal assumption in case-based reasoning (CBR) is that “similar problems have similar solutions”, learning a suitable similarity measure is an important aspect in CBR. However, learning case-case similarities is often a non-trivial task and involves significant amount of domain expertise. Most techniques that arrive at a pertinent similarity measure are often incomprehensible to the domain experts. These techniques also rarely enable the user to provide expert feedback which can then be utilized to develop better similarity measures. Our work attempts to bridge this knowledge gap by developing an iterative and interactive visualization framework called iCaseViz which learns the domain experts’ notion of similarity by utilizing the user feedback. This work is different from similar work in other communities in the sense that it is tailored to cater to the needs of a system built primarily based on the CBR hypothesis. The case base visualizer demonstrated in this paper is also very efficient as it has insignificant delay during real-time user interaction on large case bases. We provide preliminary results on the efficiency of the visualizer and the effectiveness of our similarity learning algorithm on UCI datasets and a real world high dimensional case base.

[1]  Barry Smyth,et al.  Picture Perfect: Visualisation Techniques for Case-based Reasoning , 2000, ECAI.

[2]  Conor Ryan,et al.  Artificial Intelligence and Cognitive Science , 2002, Lecture Notes in Computer Science.

[3]  Deepak Khemani,et al.  Case Based Interpretation of Soil Chromatograms , 2008, ECCBR.

[4]  David W. Aha,et al.  Tolerating Noisy, Irrelevant and Novel Attributes in Instance-Based Learning Algorithms , 1992, Int. J. Man Mach. Stud..

[5]  Barry Smyth,et al.  Advances in Case-Based Reasoning , 1996, Lecture Notes in Computer Science.

[6]  Janet L. Kolodner,et al.  Case-Based Reasoning , 1989, IJCAI 1989.

[7]  Marie desJardins,et al.  Interactive visual clustering , 2007, IUI '07.

[8]  David W. Aha,et al.  Weighting Features , 1995, ICCBR.

[9]  Armin Stahl,et al.  Learning Feature Weights from Case Order Feedback , 2001, ICCBR.

[10]  Sutanu Chakraborti,et al.  Visualizing and Evaluating Complexity of Textual Case Bases , 2008, ECCBR.

[11]  Carla E. Brodley,et al.  Dis-function: Learning distance functions interactively , 2012, 2012 IEEE Conference on Visual Analytics Science and Technology (VAST).

[12]  Chris North,et al.  Observation-level interaction with statistical models for visual analytics , 2011, 2011 IEEE Conference on Visual Analytics Science and Technology (VAST).

[13]  Göran Falkman.  The Use of a Uniform Declarative Model in 3D Visualisation for Case-Based Reasoning , 2002, ECCBR.

[14]  Thomas G. Dietterich,et al.  A study of distance-based machine learning algorithms , 1994 .

[15]  Brian Mac Namee,et al.  CBTV: Visualising Case Bases for Similarity Measure Design and Selection , 2010, ICCBR.

[16]  Stephen P. Boyd,et al.  Graph Implementations for Nonsmooth Convex Programs , 2008, Recent Advances in Learning and Control.

[17]  Seiji Yamada,et al.  An Interactive Tool for Human Active Learning in Constrained Clustering , 2011 .

[18]  David W. Aha,et al.  A Review and Empirical Evaluation of Feature Weighting Methods for a Class of Lazy Learning Algorithms , 1997, Artificial Intelligence Review.

[19]  Alfred Inselberg,et al.  Parallel coordinates for visualizing multi-dimensional geometry , 1987 .

[20]  Barry Smyth,et al.  An Interactive Visualisation Tool for Case-Based Reasoners , 2001, Applied Intelligence.

[21]  Stephen P. Boyd,et al.  Recent Advances in Learning and Control , 2008, Lecture Notes in Control and Information Sciences.

[22]  Luc Lamontagne,et al.  Case-Based Reasoning Research and Development , 1997, Lecture Notes in Computer Science.

[23]  Barry Smyth,et al.  Creating Visualizations: A Case-Based Reasoning Perspective , 2009, AICS.

[24]  James Davey,et al.  Guiding feature subset selection with an interactive visualization , 2011, 2011 IEEE Conference on Visual Analytics Science and Technology (VAST).

[25]  Patrick J. F. Groenen,et al.  Modern Multidimensional Scaling: Theory and Applications , 2003 .

[26]  Padraig Cunningham,et al.  A Taxonomy of Similarity Mechanisms for Case-Based Reasoning , 2009, IEEE Transactions on Knowledge and Data Engineering.

[27]  Sutanu Chakraborti,et al.  Feature Weighting and Confidence Based Prediction for Case Based Reasoning Systems , 2012, ICCBR.