Joint Transfer and Batch-mode Active Learning

Rita Chattopadhyay, Wei Fan, Ian Davidson, Sethuraman Panchanathan, Jieping Ye
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(3):253-261, 2013.

Abstract

Active learning and transfer learning are two different methodologies that address the common problem of insufficient labels. Transfer learning addresses this problem by using the knowledge gained from a related and already labeled data source, whereas active learning focuses on selecting a small set of informative samples for manual annotation. Recently, there has been much interest in developing frameworks that combine both transfer and active learning methodologies. A few such frameworks reported in literature perform transfer and active learning in two separate stages. In this work, we present an integrated framework that performs transfer and active learning simultaneously by solving a single convex optimization problem. The proposed framework computes the weights of source domain data and selects the samples from the target domain data simultaneously, by minimizing a common objective of reducing distribution difference between the data set consisting of reweighted source and the queried target domain data and the set of unlabeled target domain data. Comprehensive experiments on three real world data sets demonstrate that the proposed method improves the classification accuracy by 5% to 10% over the existing two-stage approach

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-chattopadhyay13, title = {Joint Transfer and Batch-mode Active Learning}, author = {Chattopadhyay, Rita and Fan, Wei and Davidson, Ian and Panchanathan, Sethuraman and Ye, Jieping}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {253--261}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {3}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/chattopadhyay13.pdf}, url = {https://proceedings.mlr.press/v28/chattopadhyay13.html}, abstract = {Active learning and transfer learning are two different methodologies that address the common problem of insufficient labels. Transfer learning addresses this problem by using the knowledge gained from a related and already labeled data source, whereas active learning focuses on selecting a small set of informative samples for manual annotation. Recently, there has been much interest in developing frameworks that combine both transfer and active learning methodologies. A few such frameworks reported in literature perform transfer and active learning in two separate stages. In this work, we present an integrated framework that performs transfer and active learning simultaneously by solving a single convex optimization problem. The proposed framework computes the weights of source domain data and selects the samples from the target domain data simultaneously, by minimizing a common objective of reducing distribution difference between the data set consisting of reweighted source and the queried target domain data and the set of unlabeled target domain data. Comprehensive experiments on three real world data sets demonstrate that the proposed method improves the classification accuracy by 5% to 10% over the existing two-stage approach} }
Endnote
%0 Conference Paper %T Joint Transfer and Batch-mode Active Learning %A Rita Chattopadhyay %A Wei Fan %A Ian Davidson %A Sethuraman Panchanathan %A Jieping Ye %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-chattopadhyay13 %I PMLR %P 253--261 %U https://proceedings.mlr.press/v28/chattopadhyay13.html %V 28 %N 3 %X Active learning and transfer learning are two different methodologies that address the common problem of insufficient labels. Transfer learning addresses this problem by using the knowledge gained from a related and already labeled data source, whereas active learning focuses on selecting a small set of informative samples for manual annotation. Recently, there has been much interest in developing frameworks that combine both transfer and active learning methodologies. A few such frameworks reported in literature perform transfer and active learning in two separate stages. In this work, we present an integrated framework that performs transfer and active learning simultaneously by solving a single convex optimization problem. The proposed framework computes the weights of source domain data and selects the samples from the target domain data simultaneously, by minimizing a common objective of reducing distribution difference between the data set consisting of reweighted source and the queried target domain data and the set of unlabeled target domain data. Comprehensive experiments on three real world data sets demonstrate that the proposed method improves the classification accuracy by 5% to 10% over the existing two-stage approach
RIS
TY - CPAPER TI - Joint Transfer and Batch-mode Active Learning AU - Rita Chattopadhyay AU - Wei Fan AU - Ian Davidson AU - Sethuraman Panchanathan AU - Jieping Ye BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/05/26 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-chattopadhyay13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 3 SP - 253 EP - 261 L1 - http://proceedings.mlr.press/v28/chattopadhyay13.pdf UR - https://proceedings.mlr.press/v28/chattopadhyay13.html AB - Active learning and transfer learning are two different methodologies that address the common problem of insufficient labels. Transfer learning addresses this problem by using the knowledge gained from a related and already labeled data source, whereas active learning focuses on selecting a small set of informative samples for manual annotation. Recently, there has been much interest in developing frameworks that combine both transfer and active learning methodologies. A few such frameworks reported in literature perform transfer and active learning in two separate stages. In this work, we present an integrated framework that performs transfer and active learning simultaneously by solving a single convex optimization problem. The proposed framework computes the weights of source domain data and selects the samples from the target domain data simultaneously, by minimizing a common objective of reducing distribution difference between the data set consisting of reweighted source and the queried target domain data and the set of unlabeled target domain data. Comprehensive experiments on three real world data sets demonstrate that the proposed method improves the classification accuracy by 5% to 10% over the existing two-stage approach ER -
APA
Chattopadhyay, R., Fan, W., Davidson, I., Panchanathan, S. & Ye, J.. (2013). Joint Transfer and Batch-mode Active Learning. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(3):253-261 Available from https://proceedings.mlr.press/v28/chattopadhyay13.html.

Related Material