New Regularized Algorithms for Transductive Learning
Abstract
We propose a new graph-based label propagation algorithm for transductive learning. Each example is associated with a vertex in an undirected graph and a weighted edge between two vertices represents similarity between the two corresponding example. We build on Adsorption, a recently proposed algorithm and analyze its properties. We then state our learning algorithm as a convex optimization problem over multi-label assignments and derive an efficient algorithm to solve this problem. We state the conditions under which our algorithm is guaranteed to converge. We provide experimental evidence on various real-world datasets demonstrating the effectiveness of our algorithm over other algorithms for such problems. We also show that our algorithm can be extended to incorporate additional prior information, and demonstrate it with classifying data where the labels are not mutually exclusive.
Cite
Text
Talukdar and Crammer. "New Regularized Algorithms for Transductive Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009. doi:10.1007/978-3-642-04174-7_29Markdown
[Talukdar and Crammer. "New Regularized Algorithms for Transductive Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2009.](https://mlanthology.org/ecmlpkdd/2009/talukdar2009ecmlpkdd-new/) doi:10.1007/978-3-642-04174-7_29BibTeX
@inproceedings{talukdar2009ecmlpkdd-new,
title = {{New Regularized Algorithms for Transductive Learning}},
author = {Talukdar, Partha Pratim and Crammer, Koby},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2009},
pages = {442-457},
doi = {10.1007/978-3-642-04174-7_29},
url = {https://mlanthology.org/ecmlpkdd/2009/talukdar2009ecmlpkdd-new/}
}