Department of Computer Science

Machine Learning Research Group

University of Texas at Austin Artificial Intelligence Lab

Publications: Active Learning

Active learning differs from passive "learning from examples" in that the learning algorithm itself attempts to select the most informative data for training. Since supervised labeling of data is expensive, active learning attempts to reduce the human effort needed to learn an accurate result by selecting only the most informative examples for labeling. Our work has focused on diverse ensembles for active learning and applications of active learning to problems in natural-language processing and semi-supervised learning. We have also addressed the problem of actively acquiring the most useful features values of examples as well as supervised class labels.

Show abstracts
  1. Dialog Policy Learning for Joint Clarification and Active Learning Queries
    [Details] [PDF] [Slides (PDF)] [Poster] [Video]
    Aishwarya Padmakumar, Raymond J. Mooney
    In The AAAI Conference on Artificial Intelligence (AAAI), February 2021.
  2. Dialog as a Vehicle for Lifelong Learning of Grounded Language Understanding Systems
    [Details] [PDF] [Slides (PDF)]
    Aishwarya Padmakumar
    PhD Thesis, Department of Computer Science, The University of Texas at Austin, August 2020.
  3. Dialog as a Vehicle for Lifelong Learning
    [Details] [PDF] [Slides (PDF)] [Video]
    Aishwarya Padmakumar, Raymond J. Mooney
    In Position Paper Track at the SIGDIAL Special Session on Physically Situated Dialogue (RoboDial 2.0), July 2020.
  4. Improving Grounded Natural Language Understanding through Human-Robot Dialog
    [Details] [PDF]
    Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney
    In IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, May 2019.
  5. Learning a Policy for Opportunistic Active Learning
    [Details] [PDF]
    Aishwarya Padmakumar, Peter Stone, Raymond J. Mooney
    In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-18), Brussels, Belgium, November 2018.
  6. Improved Models and Queries for Grounded Human-Robot Dialog
    [Details] [PDF]
    Aishwarya Padmakumar
    October 2018. PhD Proposal, Department of Computer Science, The University of Texas At Austin.
  7. Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog
    [Details] [PDF]
    Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney
    In Late-breaking Track at the SIGDIAL Special Session on Physically Situated Dialogue (RoboDIAL-18), Melbourne, Australia, July 2018.
  8. Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog
    [Details] [PDF]
    Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney
    In RSS Workshop on Models and Representations for Natural Human-Robot Communication (MRHRC-18). Robotics: Science and Systems (RSS), June 2018.
  9. Opportunistic Active Learning for Grounding Natural Language Descriptions
    [Details] [PDF]
    Jesse Thomason and Aishwarya Padmakumar and Jivko Sinapov and Justin Hart and Peter Stone and Raymond J. Mooney
    In Sergey Levine and Vincent Vanhoucke and Ken Goldberg, editors, Proceedings of the 1st Annual Conference on Robot Learning (CoRL-17), 67--76, Mountain View, California, November 2017. PMLR.
  10. Knowledge Transfer Using Latent Variable Models
    [Details] [PDF] [Slides (PDF)]
    Ayan Acharya
    PhD Thesis, Department of Electrical and Computer Engineering, The University of Texas at Austin, August 2015.
  11. Active Multitask Learning Using Both Latent and Supervised Shared Topics
    [Details] [PDF] [Slides (PDF)]
    Ayan Acharya and Raymond J. Mooney and Joydeep Ghosh
    In Proceedings of the 2014 SIAM International Conference on Data Mining (SDM14), Philadelphia, Pennsylvania, April 2014.
  12. Using Active Relocation to Aid Reinforcement Learning
    [Details] [PDF]
    Lilyana Mihalkova and Raymond Mooney
    In Prodeedings of the 19th International FLAIRS Conference (FLAIRS-2006), 580-585, Melbourne Beach, FL, May 2006.
  13. Creating Diverse Ensemble Classifiers to Reduce Supervision
    [Details] [PDF]
    Prem Melville
    PhD Thesis, Department of Computer Sciences, University of Texas at Austin, November 2005. 141 pages. Technical Report TR-05-49.
  14. An Expected Utility Approach to Active Feature-value Acquisition
    [Details] [PDF]
    P. Melville, M. Saar-Tsechansky, F. Provost and Raymond J. Mooney
    In Proceedings of the International Conference on Data Mining, 745-748, Houston, TX, November 2005.
  15. Semi-supervised Clustering: Probabilistic Models, Algorithms and Experiments
    [Details] [PDF]
    Sugato Basu
    PhD Thesis, University of Texas at Austin, 2005.
  16. Economical Active Feature-value Acquisition through Expected Utility Estimation
    [Details] [PDF]
    P. Melville, M. Saar-Tsechansky, F. Provost and Raymond J. Mooney
    In Proceedings of the KDD-05 Workshop on Utility-Based Data Mining, 10-16, Chicago, IL, August 2005.
  17. Active Learning for Probability Estimation using Jensen-Shannon Divergence
    [Details] [PDF]
    P. Melville, S. M. Yang, M. Saar-Tsechansky and Raymond J. Mooney
    In Proceedings of the 16th European Conference on Machine Learning, 268--279, Porto, Portugal, October 2005.
  18. Active Feature-Value Acquisition for Classifier Induction
    [Details] [PDF]
    Prem Melville, Maytal Saar-Tsechansky, Foster Provost, and Raymond J. Mooney
    Technical Report UT-AI-TR-04-311, Artificial Intelligence Lab, University of Texas at Austin, February 2004.
  19. Active Feature-Value Acquisition for Classifier Induction
    [Details] [PDF]
    Prem Melville, Maytal Saar-Tsechansky, Foster Provost, and Raymond J. Mooney
    In Proceedings of the Fourth IEEE International Conference on Data Mining (ICDM-2004), 483-486, Brighton, UK, November 2004.
  20. Diverse Ensembles for Active Learning
    [Details] [PDF]
    Prem Melville and Raymond J. Mooney
    In Proceedings of 21st International Conference on Machine Learning (ICML-2004), 584-591, Banff, Canada, July 2004.
  21. Active Semi-Supervision for Pairwise Constrained Clustering
    [Details] [PDF]
    Sugato Basu, Arindam Banerjee, and Raymond J. Mooney
    In Proceedings of the 2004 SIAM International Conference on Data Mining (SDM-04), April 2004.
  22. Active Learning for Natural Language Parsing and Information Extraction
    [Details] [PDF]
    Cynthia A. Thompson, Mary Elaine Califf and Raymond J. Mooney
    In Proceedings of the Sixteenth International Conference on Machine Learning (ICML-99), 406-414, Bled, Slovenia, June 1999.