A Context-Aware Approach to Selecting Adaptations for Case-Based Reasoning

Jalali, Vahid; Leake, David

doi:10.1007/978-3-642-40972-1_8

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given BEAR's efficiency, we also intend to extend our methods to test more computationally expensive variations of the EAR family of methods as the case-base estimator module in BEAR. For example, generating rules from neighborhoods other than the local neighborhood of the input query-which requires consideration of many more cases-and adding contextual considerations in adaptation retrieval, have produced good small-scale results [10], but with high costs that raised concerns for their large-scale applicability by conventional CBR methods. The BEAR framework suggests a path for making practical such case-intensive methods.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Jalali

Leake

2015

Case-Based Reasoning Research and Development

Self Cite

View full text Add to dashboard Cite

Abstract. Adaptation knowledge generation is a difficult problem for CBR. In previous work we developed ensembles of adaptation for regression (EAR), a family of methods for generating and applying ensembles of adaptation rules for case-based regression. EAR has been shown to provide good performance, but at the cost of high computational complexity. When efficiency problems result from case base growth, a common CBR approach is to focus on case base maintenance, to compress the case base. This paper presents a case study of an alternative approach, harnessing big data methods, specifically MapReduce and locality sensitive hashing (LSH), to make the EAR approach feasible for large case bases without compression. Experimental results show that the new method, BEAR, substantially increases accuracy compared to a baseline big data k-NN method using LSH. BEAR's accuracy is comparable to that of traditional k-NN without using LSH, while its processing time remains reasonable for a case base of millions of cases. We suggest that increased use of big data methods in CBR has the potential for a departure from compression-based case-base maintenance methods, with their concomitant solution quality penalty, to enable the benefits of full case bases at much larger scales.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This work demonstrated the accuracy benefits of EAR [9][10][11][12], but also identified important efficiency concerns for large case bases. This paper presents a case study applying big data methods to addressing EAR's scale-up, leveraging techniques and frameworks well known to the big data community to enable large-scale CBR.…”

Section: Introductionmentioning

confidence: 86%

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Jalali

Leake

2015

Case-Based Reasoning Research and Development

Self Cite

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, none of the existing case-based regression methods using both retrieval and adaptation has been used for case base maintenance, so no exact comparison points are available in the literature. However, if they were applied under the same independence assumption introduced in AGCBM1 (that the case and adaptation contributions can be assessed separately), they would correspond to weakened versions of AGCBM1, in that tests of CAAR (used in AGCBM1) show its results to be more accurate than other retrieval plus adaptation methods (Jalali and Leake 2013a).…”

Section: Methodsmentioning

confidence: 99%

Adaptation-Guided Case Base Maintenance

Jalali

Leake

2014

AAAI

Self Cite

View full text Add to dashboard Cite

In case-based reasoning (CBR), problems are solved by retrieving prior cases and adapting their solutions to fit; learning occurs as new cases are stored. Controlling the growth of the case base is a fundamental problem, and research on case-base maintenance has developed methods for compacting case bases while maintaining system competence, primarily by competence-based deletion strategies assuming static case adaptation knowledge. This paper proposes adaptation-guided case-base maintenance (AGCBM), a case-base maintenance approach exploiting the ability to dynamically generate new adaptation knowledge from cases. In AGCBM, case retention decisions are based both on cases' value as base cases for solving problems and on their value for generating new adaptation rules. he paper illustrates the method for numerical prediction tasks (case-based regression) in which adaptation rules are generated automatically using the case difference heuristic. In comparisons of AGCBM to five alternative methods in four domains, for varying case base densities, AGCBM outperformed the alternatives in all domains, with greatest benefit at high compression.

show abstract

“…Adaptation is based on an anchor mapping algorithm which identifies the parts of the workflow where to apply the changes. In [22], a method for increasing the context-awareness of case adaptation is proposed, with an application to a regression task. In this work, the context is used to improve the quality of adaptation rules that can be automatically extracted from the comparison of the cases.…”

Section: Related Workmentioning

confidence: 99%

Differential adaptation: An operational approach to adaptation for solving numerical problems with CBR

Fuchs

Lieber

Mille

et al. 2014

Knowledge-Based Systems

View full text Add to dashboard Cite

Case-based reasoning relies on four main steps: retrieval, adaptation, revision and retention. This article focuses on the adaptation step; we propose differential adaptation as an operational formalization of adaptation for numerical problems. The solution to a target problem is designed on the basis of relations existing between a source case (problem and solution) and a target case. Differential adaptation relies on the metaphor of differential calculus where small variations on variable values are related to variations of function values. Accordingly, variations between problems correspond to variations between variable values and variations between solutions to variations between function values. Operators inspired from differential calculus are able to manipulate the variations and to support the whole adaptation process. Differential adaptation is operational and provides generic operators that can be reused for different real-world numerical situations.

show abstract

A Context-Aware Approach to Selecting Adaptations for Case-Based Reasoning

Cited by 11 publications

References 10 publications

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Adaptation-Guided Case Base Maintenance

Differential adaptation: An operational approach to adaptation for solving numerical problems with CBR

Contact Info

Product

Resources

About