@conference {14443, title = {Effective label acquisition for collective classification}, booktitle = {Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining}, series = {KDD {\textquoteright}08}, year = {2008}, month = {2008///}, pages = {43 - 51}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Information diffusion, viral marketing, and collective classification all attempt to model and exploit the relationships in a network to make inferences about the labels of nodes. A variety of techniques have been introduced and methods that combine attribute information and neighboring label information have been shown to be effective for collective labeling of the nodes in a network. However, in part because of the correlation between node labels that the techniques exploit, it is easy to find cases in which, once a misclassification is made, incorrect information propagates throughout the network. This problem can be mitigated if the system is allowed to judiciously acquire the labels for a small number of nodes. Unfortunately, under relatively general assumptions, determining the optimal set of labels to acquire is intractable. Here we propose an acquisition method that learns the cases when a given collective classification algorithm makes mistakes, and suggests acquisitions to correct those mistakes. We empirically show on both real and synthetic datasets that this method significantly outperforms a greedy approximate inference approach, a viral marketing approach, and approaches based on network structural measures such as node degree and network clustering. In addition to significantly improving accuracy with just a small amount of labeled data, our method is tractable on large networks.}, keywords = {active inference, collective classification, label acquisition}, isbn = {978-1-60558-193-4}, doi = {10.1145/1401890.1401901}, url = {http://doi.acm.org/10.1145/1401890.1401901}, author = {Bilgic,Mustafa and Getoor, Lise} }