Sciweavers

Share
NIPS
2008

Regularized Learning with Networks of Features

11 years 1 months ago
Regularized Learning with Networks of Features
For many supervised learning problems, we possess prior knowledge about which features yield similar information about the target variable. In predicting the topic of a document, we might know that two words are synonyms, and when performing image recognition, we know which pixels are adjacent. Such synonymous or neighboring features are near-duplicates and should be expected to have similar weights in an accurate model. Here we present a framework for regularized learning when one has prior knowledge about which features are expected to have similar and dissimilar weights. The prior knowledge is encoded as a network whose vertices are features and whose edges represent similarities and dissimilarities between them. During learning, each feature's weight is penalized by the amount it differs from the average weight of its neighbors. For text classification, regularization using networks of word co-occurrences outperforms manifold learning and compares favorably to other recently ...
Ted Sandler, John Blitzer, Partha Pratim Talukdar,
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where NIPS
Authors Ted Sandler, John Blitzer, Partha Pratim Talukdar, Lyle H. Ungar
Comments (0)
books