Introduction to algorithms
Exploring Unknown Environments
SIAM Journal on Computing
Regular Article: A Structured Family of Clustering and Tree Construction Methods
Advances in Applied Mathematics
Diffusion Kernels on Graphs and Other Discrete Input Spaces
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Learning from Labeled and Unlabeled Data using Graph Mincuts
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Semi-supervised learning using randomized mincuts
ICML '04 Proceedings of the twenty-first international conference on Machine learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
An analysis of graph cut size for transductive learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
On an Online Spanning Tree Problem in Randomly Weighted Graphs
Combinatorics, Probability and Computing
Discovering cohesive subgroups from social networks for targeted advertising
Expert Systems with Applications: An International Journal
A discriminative framework for clustering via similarity functions
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science
Exploiting Cluster-Structure to Predict the Labeling of a Graph
ALT '08 Proceedings of the 19th international conference on Algorithmic Learning Theory
| Hi-index | 5.23 |
Motivated by a problem of targeted advertising in social networks, we introduce a new model of online learning on labeled graphs where the graph is initially unknown and the algorithm is free to choose which vertex to predict next. For this learning model, we define an appropriate measure of regularity of a graph labeling called the merging degree. In general, the merging degree of a graph is small when its vertices can be partitioned into a few well-separated clusters within which labels are roughly constant. For the special case of binary labeled graphs, the merging degree is a more refined measure than the cutsize. After observing that natural nonadaptive exploration/prediction strategies, like depth-first with majority vote, do not behave satisfactorily on graphs with small merging degree, we introduce an efficiently implementable adaptive strategy whose cumulative loss is controlled by the merging degree. A matching lower bound shows that in the case of binary labels our analysis cannot be improved.