Random Forests for Metric Learning with Implicit Pairwise Position Dependence

Details Random Forests for Metric Learning with Implicit Pairwise Position Dependence Random Forests for Metric Learning with Implicit Pairwise Position Dependence

2012-01-03

arxiv.org/abs/1201.0610v1

Statistics

Machine Learning

Scientific paper

Metric learning makes it plausible to learn distances for complex distributions of data from labeled data. However, to date, most metric learning methods are based on a single Mahalanobis metric, which cannot handle heterogeneous data well. Those that learn multiple metrics throughout the space have demonstrated superior accuracy, but at the cost of computational efficiency. Here, we take a new angle to the metric learning problem and learn a single metric that is able to implicitly adapt its distance function throughout the feature space. This metric adaptation is accomplished by using a random forest-based classifier to underpin the distance function and incorporate both absolute pairwise position and standard relative position into the representation. We have implemented and tested our method against state of the art global and multi-metric methods on a variety of data sets. Overall, the proposed method outperforms both types of methods in terms of accuracy (consistently ranked first) and is an order of magnitude faster than state of the art multi-metric methods (16x faster in the worst case).

Affiliated with

Also associated with

No associations

Rating

Random Forests for Metric Learning with Implicit Pairwise Position Dependence does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Random Forests for Metric Learning with Implicit Pairwise Position Dependence, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Random Forests for Metric Learning with Implicit Pairwise Position Dependence will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-183711