Case-base maintenance strategies judiciously choose the most valuable cases to retain and the least valuable cases to delete in order to maintain a compact, competent case base. This research summary presents three case-base maintenance strategies which involve more than merely deleting cases: (1) Flexible feature deletion deletes components of cases instead of whole cases. (2) Adaptation-guided feature deletion prioritizes components for deletion according to their recoverability via adaptation knowledge. (3) Expansion-contraction compression, in addition to deleting cases, also adds cases in unexplored regions of the problem space. Evaluation of the strategies compared to standard case-base maintenance shows improved retention of competence and solution quality for suitable data sets compressed to the same sizes.
Case-based reasoning gradually builds up a case base from training data, knowledge engineered by human experts, and the retention phase. Each case retained in the case base can potentially, through adaptation, solve future problems. On the other hand, each retained case makes the case base larger. A larger case base requires more storage, more time to search through, more time to transmit over a network, and more time to manually review.
The swamping utility problem describes this trade-o between the
competence, quality, and speed contribution of a case versus its storage, retrieval, and
bandwidth cost [
Case-base maintenance strategies, whether based on coverage and
reachability or not, normally make two assumptions: (1) that all cases have a uniform
storage cost and (2) that they must retain or delete whole cases. This research
summary describes exible feature deletion, a knowledge-light case-base
maintenance strategy which, in contrast, subdivides variable-size cases for deletion of
their components [
Cases can have varying storage cost when they contain varying amounts of information at varying levels of detail. The storage cost of both the problem and the solution can vary independently because a simple problem may have a complex solution and vice versa. This suggests balancing the competence contribution of a case against its storage cost.
A case-base maintenance strategy could delete an entire case, but it could also delete a single feature across all cases, or a single feature from a single case. Each of these alternatives presumably degrades problem-solving competence but not necessarily to the same degree. Compared to per-case strategies, exible feature deletion could reduce the size of a case base with less reduction in the number of cases. It could also vary in the metric that it uses to order features for deletion. Each of the variations uses a knowledge-light metric like the size of a case, the rarity of a feature, or a hybrid of multiple metrics.
Domains with large cases and multiple representations call for the application of exible feature deletion. For example, cases based on medical imagery may have various resolutions and a large number of features of which only some are relevant to the diagnosis. 3
The adaptation-guided feature deletion case-base maintenance strategy builds
on exible feature deletion. Whereas exible feature deletion orders the features
according to a knowledge-light metric, adaptation-guided feature deletion
integrates additional knowledge from the solution transformation container about
the recoverability of features [
A solution with recovered features may either match exactly the original uncompressed solution, or it may solve the same problem in a di erent way. Compression to smaller sizes can increase the time required for recovery and decrease the quality of the recovered solution until adaptation knowledge can no longer recover any solution at all. Therefore, in order to preserve problemsolving competence, adaptation-guided feature deletion deletes features in order from most recoverable to least.
In addition to deleting features, adaptation-guided feature deletion can also replace them with a smaller substitution or abstraction. Occasionally, this reorganization can make case contents more accessible to an adaptation rule of limited power. Even though case-base compression normally reduces competence, compression under these circumstances, termed creative destruction, can improve competence instead. 4
By the representativeness assumption, maintenance strategies predict that future problems will follow the same distribution as the current case base, and this works reasonably well for mature case bases in stable domains. But the representativeness assumption may apply less accurately during early case base growth, to dynamically changing domains, or in cross-domain transfer learning.
In these situations, case-base maintenance strategies optimizing for assumed
representativeness may instead cause over tting. Over tting means that a
statistical model or a machine learning algorithm makes predictions based on
peculiarities in the training data not re ected in the testing data thereby improving
performance on the training data and sacri cing performance on the testing data
[
The over tting problem has received signi cant attention in the context of
arti cial neural networks [
No Gap
Medium Gap CNN
ECC Large Gap 100% 90% 80% 70% 60% 50% 40% 30% 20% 10% 100% 90% 80% 70% 60% 50% 40% 30% 20% 10% out obscuring their subjects or other minor deformations which maintain overall cohesion.
Case-based reasoning does not normally apply data augmentation, but the
solution transformation container provides a natural source for such
perturbations. Expansion-contraction compression explores unseen regions of the problem
space using adaptation knowledge to generate ghost cases and then exploits the
ghost cases to broaden the range of cases available for competence-based deletion
[
Expansion-contraction compression explores the problem space arbitrarily |
not necessarily in the direction of unrepresentative regions. Therefore, similar to
[
This research summary anticipates a dissertation consisting of six chapters. The rst chapter will describe the case-based reasoning cycle and motivate casebased maintenance in terms of the swamping utility problem. The second chapter will explain the uniform storage and indivisiblity assumptions and evaluate exible feature deletion. The third chapter will de ne recoverability and evaluate adaptation-guided feature deletion. The fourth chapter will explain the representativeness assumption and over tting problem and evaluate expansioncontraction compression. The fth chapter will explain competence groups and competence holes and evaluate targeted expansion-contraction compression. The sixth chapter will envision future work and conclude by restating the key contributions.