| P.-O. Fjallstrom. Algorithms for graph partitioning: A survey. Linkoping Electronic Atricles in Computer and Information Science, 3, 1998. |
....cut. The two resulting sets of nodes (words) then form the feature split to which co training can be applied. However, step 3 of the algorithm is NP hard so we need to use e#cient approximation algorithms. Fortunately, much is known about e#cient approximate min cut graph partitioning algorithms [9]. Experiments using this approach, and ideas in similar directions, are an area of ongoing research. 7. DISCUSSION AND FUTURE WORK Given the results from the previous sections, what can we conclude about the behavior of co training Certainly, results on the News 2x2 dataset show that ....
P.-O. Fjallstrom. Algorithms for graph partitioning: A survey. Linkoping Electronic Atricles in Computer and Information Science, 3, 1998.
No context found.
P.-O. Fjallstrom. Algorithms for graph partitioning: A survey. Linkoping Electronic Atricles in Computer and Information Science, 3, 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC