Instance Label Prediction by Dirichlet Process Multiple Instance Learning

Melih Kandemir Heidelberg University HCI/IWR, Fred Hamprecht Heidelberg University HCI/IWR
Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, PMLR R12:294-303, 2014.

Abstract

We propose a generative Bayesian model that predicts instance labels from weak (bag-level) supervision. We solve this problem by simultaneously modeling class distributions by Gaussian mixture models and inferring the class labels of positive bag instances that satisfy the multiple instance constraints. We employ Dirichlet process priors on mixture weights to automate model selection, and efficiently infer model parameters and positive bag instances by a constrained variational Bayes procedure. Our method improves on the state-of-the-art of instance classification from weak supervision on 20 benchmark text categorization data sets and one histopathology cancer diagnosis data set.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR12-hci-iwr14a, title = {Instance Label Prediction by {D}irichlet Process Multiple Instance Learning}, author = {HCI/IWR, Melih Kandemir Heidelberg University and HCI/IWR, Fred Hamprecht Heidelberg University}, booktitle = {Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence}, pages = {294--303}, year = {2014}, editor = {Zhang, Nevin L. and Tian, Jin}, volume = {R12}, series = {Proceedings of Machine Learning Research}, month = {23--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r12/main/assets/hci-iwr14a/hci-iwr14a.pdf}, url = {https://proceedings.mlr.press/r12/hci-iwr14a.html}, abstract = {We propose a generative Bayesian model that predicts instance labels from weak (bag-level) supervision. We solve this problem by simultaneously modeling class distributions by Gaussian mixture models and inferring the class labels of positive bag instances that satisfy the multiple instance constraints. We employ Dirichlet process priors on mixture weights to automate model selection, and efficiently infer model parameters and positive bag instances by a constrained variational Bayes procedure. Our method improves on the state-of-the-art of instance classification from weak supervision on 20 benchmark text categorization data sets and one histopathology cancer diagnosis data set.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Instance Label Prediction by Dirichlet Process Multiple Instance Learning %A Melih Kandemir Heidelberg University HCI/IWR %A Fred Hamprecht Heidelberg University HCI/IWR %B Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2014 %E Nevin L. Zhang %E Jin Tian %F pmlr-vR12-hci-iwr14a %I PMLR %P 294--303 %U https://proceedings.mlr.press/r12/hci-iwr14a.html %V R12 %X We propose a generative Bayesian model that predicts instance labels from weak (bag-level) supervision. We solve this problem by simultaneously modeling class distributions by Gaussian mixture models and inferring the class labels of positive bag instances that satisfy the multiple instance constraints. We employ Dirichlet process priors on mixture weights to automate model selection, and efficiently infer model parameters and positive bag instances by a constrained variational Bayes procedure. Our method improves on the state-of-the-art of instance classification from weak supervision on 20 benchmark text categorization data sets and one histopathology cancer diagnosis data set. %Z Reissued by PMLR on 04 October 2026.
APA
HCI/IWR, M.K.H.U. & HCI/IWR, F.H.H.U.. (2014). Instance Label Prediction by Dirichlet Process Multiple Instance Learning. Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R12:294-303 Available from https://proceedings.mlr.press/r12/hci-iwr14a.html. Reissued by PMLR on 04 October 2026.

Related Material