Random Projection is a method for projecting high dimensional (and often sparse) data into a lower dimensional (and less sparse) representation. It has so far shown good performance on a number of tasks, and good scaling potential.

Here is a very brief bibliography.

Magnus Sahlgren. An introduction to random indexing. Technical report, 2005. http://www.sics.se/~mange/papers/RI_intro.pdf.

See also the excellent collection at http://www.sics.se/~mange/random_indexing.html.

Ella Bingham and Heikki Mannila. Random projection in dimensionality reduction: applications to image and text data. In Knowledge Discovery and Data Mining, pages 245–250, 2001. http://citeseer.ist.psu.edu/bingham01random.html.

Pentti Kanerva. Sparse Distributed Memory. MIT Press, 1988.