Machine Learning Research Group Meetings

[ Meeting Schedule | Participants | Links | Proposed Papers | Previous Discussions ]

We read and discuss papers in the area of machine learning.

Regular Meeting Time & Place

• The Machine Learning meetings have been subsumed by the Data Minining group as of Fall 2008.  

• The Natural Language Acquisition Group's page can be found here.

Next Scheduled Meetings

Date	Time	Place	agenda

* Future meetings subject to rearrangement.
* Please send in suggestions for new papers to discuss, or vote for a paper from the currently proposed papers.

Past Meetings

Date	Time	Place	agenda
8/13/2008	2PM	ACES 5.444	Jurgen Van Gael, Yunus Saatci, Yee Whye Teh and Zoubin Ghahramani Beam Sampling for the Infinite Hidden Markov Model, ICML 2008
6/4/2008	2PM	ACES 5.444	Yisong Yue and Thorsten Joachims Predicting Diverse Subsets Using Structural SVMs, ICML 2008
5/21/2008	2PM	ACES 5.444	Rodrigo B. Almeida, Virglio A. F. Almeida A Community-Aware Search Engine, International Conference on World Wide Web, 2004
4/30/2008	5PM	ACES 5.444	J. Davis, B. Kulis, P. Jain, S. Sra, I. Dhillon Information-theoretic Metric Learning, ICML 2007 Best Student Paper Award
4/16/2008	5PM	ACES 5.444	Charles Parker, Alan Fern, and Prasad Tadepalli Learning for efficient retrieval of structured data with noisy queries, ICML 2007
4/2/2008	5PM	ACES 5.444	B. Taskar, C. Guestrin and D. Koller Max-Margin Markov Networks, NIPS 2003
3/19/2008	5PM	ACES 5.444	A. Banerjee, S. Basu Topic Models over Text Streams: A Study of Batch and Online Unsupervised Learning, SDM 2007
2/27/2008	5PM	ACES 5.444	Dafna Shahaf and Eyal Amir Learning Partially Observable Action Schemas, AAAI 2006
2/13/2008	5PM	ACES 5.444	Tuyen Huynh and Raymond J. Mooney Discriminative Structure and P\ arameter Learning for Markov Logic Networks, Under submission to ICML 2008

For older discussions, please see Previous Discussions

Current Participants

• Ray Mooney --- (mooney@cs.utexas.edu)

• Katrin Erk --- (katrin.erk@gmail.com)

• Jason Baldridge --- (jasonbaldridge@gmail.com)

• Ruifang Ge --- (grf@cs.utexas.edu)

• Lilyana Mihalkova --- (lilyanam@cs.utexas.edu)

• Tuyen Ngoc Huynh --- (hntuyen@cs.utexas.edu)

• Matt Taylor --- (mtaylor@cs.utexas.edu)

• Sonal Gupta --- (sonaluta@cs.utexas.edu)

• Ben Wing --- (ben@666.com)

• Sudipta Chatterjee --- (sudipta.referral@gmail.com)

• Maytal Saar-Tsechansky --- (Maytal.Saar-Tsechansky@mccombs.utexas.edu)

• Danxia Kong (multigoldmountain@yahoo.com)

• David Chen --- (dlcc@cs.utexas.edu)

Related Links

• Machine Learning Group

• Laboratory for Artificial Neural Systems

• Data Mining Laboratory

• Forum for Artifical Intelligence (FAI)

• Data Mining Seminar Series

• Data Mining Reading Seminar

• Natural Language Acquisition Group's Reading Seminar

• The Unsupervised Learning Group's Seminar

Currently Proposed Papers

• Alex Kulesza, Fernando Pereira
  Structured Learning with Approximate Inference, NIPS 2007
  proposed by Lily

• Daniel Lowd and Pedro Domingos
  Efficient Weight Learning for Markov Logic Networks, PKDD 2007
  proposed by Tuyen

• Ruslan Salakhutdinov, Andriy Mnih, and Geoffrey Hinton
  Restricted Boltzmann Machines for Collaborative Filtering, ICML 2007
  proposed by Lily

• Matthew J. Rattigan, Marc Maier, and David Jensen
  Graph Clustering With Network Structure Indices, ICML 2007
  proposed by Lily

• Gideon S. Mann, Andrew McCallum
  Simple, Robust, Scalable Semi-supervised Learning via Expectation Regularization, ICML 2007
  proposed by Tuyen

• Roberto Esposito, Daniele P. Radicioni
  CarpeDiem: an Algorithm for the Fast Evaluation of SSL Classifiers, ICML 2007
  proposed by Tuyen

• Amir Globerson, Terry Y. Koo, Xavier Carreras, Michael Collins
  Exponentiated Gradient Algorithms for Log-Linear Structured Prediction, ICML 2007
  proposed by Tuyen, vote by Lily

• Antoine Bordes, Léon Bottou, Patrick Gallinari, Jason Westons
  Solving MultiClass Support Vector Machines with LaRank. ICML 2007
  proposed by Tuyen

• Peter Haider, Ulf Brefeld, Tobias Scheffers
  Supervised Clustering of Streaming Data for Email Batch Detection. ICML 2007
  proposed by Tuyen

• David Mimno, Wei Li, Andrew McCallum
  Mixtures of Hierarchical Topics with Pachinko Allocation. ICML 2007
  proposed by Tuyen

• Gemma C. Garriga, Roni Khardon, Luc De Raedt.
  On Mining Closed Sets in Multi-Relational Data. IJCAI 2007.
  proposed by Lily

• Jian Huang, Adrian R. Pearce.
  Collaborative Inductive Logic Programming for Path Planning. IJCAI 2007.
  proposed by Lily

• Marius Pasca, Benjamin Van Durme.
  What You Seek is What You Get: Extraction of Class Attributes from Query Logs. IJCAI 2007.
  proposed by Lily

• Yuichiro Yonebayashi, Hirokazu Kameoka, Shigeki Sagayama.
  Automatic Decision of Piano Fingering Based on a Hidden Markov Models. IJCAI 2007.
  proposed by Lily

• Hinton, G. E. and Salakhutdinov, R. R.
  Reducing the dimensionality of data with neural networks. Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.
  Also, supporting online material
  proposed by Misha

• Hanghang Tong, Christos Faloutsos, and Jia-Yu Pan.
  Fast Random Walk with Restart and Its Applications. ICDM 2006 (Best Paper Award).
  proposed by Misha

• Louis Licamele and Lise Getoor .
  Social Capital in Friendship-Event Networks. ICDM 2006.
  proposed by Misha

• Arpit Mathur and Soumen Chakrabarti.
  Accelerating Newton Optimization for Log-Linear Models through Feature Redundancy. ICDM 2006.
  proposed by Misha

• G. Chechik, G. Heitz, G. Elidan, P. Abbeel, D. Koller.
  Max-margin classification of incomplete data. NIPS 2006.
  proposed by Razvan

• Jiayuan Huang, Alex Smola, Arthur Gretton, Karsten M. Borgwardt, Bernhard Schölkopf.
  Correcting Sample Selection Bias by Unlabeled Data. NIPS 2006.
  proposed by Razvan, voted by Lily

• Andreas Argyriou, Theos Evgeniou, Massimiliano Pontil.
  Multi-Task Feature Learning . NIPS 2006.
  proposed by Razvan, voted by Lily

• Shai Ben-David, John Blitzer, Koby Crammer, and Fernando Pereira.
  Analysis of Representations for Domain Adaptation. NIPS 2006.
  proposed by Yuk Wah

• Fei Sha and Lawrence K. Saul.
  Large margin hidden Markov models for automatic speech recognition. NIPS 2006.
  proposed by Yuk Wah

  
  
  

• Lei Tang, Jianping Zhang, Huan Liu.
  Acclimatizing taxonomic semantics for hierarchical content classification from semantics to data-driven taxonomy. KDD 2006.
  proposed by Razvan

• Christian Böhm, Christos Faloutsos, Jia-Yu Pan, Claudia Plant.
  Robust information-theoretic clustering. KDD 2006.
  proposed by Razvan

• Thorsten Joachims.
  Training linear SVMs in linear time. KDD 2006 (Best Paper).
  proposed by Razvan

• Jun Zhu, Zaiqing Nie, Ji-Rong Wen, Bo Zhang, Wei-Ying Ma.
  Simultaneous record detection and attribute labeling in web data extraction. KDD 2006.
  proposed by Razvan

• Rosa I. Arriaga and Santosh Vempala.
  An algorithmic theory of learning: Robust concepts and random projection . MLJ, May 2006.
  proposed by Razvan

• Simon Colton and Stephen Muggleton.
  Mathematical applications of inductive logic programming. MLJ, Sep 2006.
  proposed by Razvan

• Helge Langseth and Thomas D. Nielsen.
  Classification using Hierarchical Naïve Bayes models. MLJ, May 2006.
  proposed by Razvan, voted by Tuyen, Matt

• Pieter Abbeel, Daphne Koller, Andrew Y. Ng.
  Learning Factor Graphs in Polynomial Time and Sample Complexity. JMLR 2006.
  proposed by Razvan

• Chen Yanover, Talya Meltzer, Yair Weiss.
  Linear Programming Relaxations and Belief Propagation -- An Empirical Study. JMLR 2006.
  proposed by Razvan

• Hema Raghavan, Omid Madani, Rosie Jones.
  Active Learning with Feedback on Features and Instances. JMLR 2006.
  proposed by Razvan, voted by Duy

• Juho Rousu, Craig Saunders, Sandor Szedmak, John Shawe-Taylor.
  Kernel-Based Learning of Hierarchical Multilabel Classification Models. JMLR 2006.
  proposed by Razvan, voted by Tuyen

• Edwin Bonilla, Chris Williams, Felix Agakov, John Cavazos, John Thomson, Michael O'Boyle.
  Predictive Search Distributions .ICML 06.
  proposed by Lily

• Wolf Kienzle, Kumar Chellapilla.
  Personalized Handwriting Recognition via Biased Regularization .ICML 06.
  proposed by Lily, voted by Yuk Wah

• Prithviraj Sen, Lise Getoor.
  Cost-Sensitive Learning with Conditional Markov Networks .ICML 06.
  proposed by Lily

• Alice Zheng, Michael Jordan, Ben Liblit, Mayur Naik, Alex Aiken.
  Statistical Debugging: Simultaneous Identification of Multiple Bugs .ICML 06.
  proposed by Lily, voted by Yuk Wah, Duy

• Brendan Juba.
  Estimating Relatedness via Data Compression .ICML 06.
  Comments from Lily: Very theoretical but problem and approach seemed interesting
  proposed by Lily

• Marc Toussaint, Amos Storkey.
  Probabilistic inference for solving discrete and continuous state Markov Decision Processes .ICML 06.
  Comments from Lily: Only talked to the person at his poster but it seemed like a very creative way of solving MDPs by boiling it down to inference in dynamic bayesian networks.
  proposed by Lily

• Jason Weston, Ronan Collobert, Fabian Sinz, Léon Bottou, Vladimir Vapnik.
  Inference with the Universum. ICML 2006.
  proposed by Razvan

• Francisco Pereira, Geoffrey Gordon.
  The Support Vector Decomposition Machine. ICML 2006.
  proposed by Razvan

• Ulf Brefeld, Tobias Scheffer.
  Semi-Supervised Learning for Structured Output Variables. ICML 2006.
  proposed by Razvan, voted by Tuyen

• Fei Wang, Changshui Zhang.
  Label Propagation through Linear Neighborhoods. ICML 2006.
  proposed by Razvan

• Ulrich Rückert, Stefan Kramer.
  A Statistical Approach to Rule Learning. ICML 2006.
  proposed by Razvan, voted by Tuyen

• Quoc V. Le, Alex J. Smola, Thomas Gärtner.
  Simpler Knowledge-based Support Vector Machines. ICML 2006.
  proposed by Razvan, voted by Duy and Matt

• Amir Globerson, Sam Roweis.
  Nightmare at Test Time: Robust Learning by Feature Deletion. ICML 2006.
  Comments: The problem seems related to the one reported in Sutton's paper on "weight undertraining" from HLT-NAACL 2006.
  proposed by Razvan

• Pierre Geurts, Louis Wehenkel, Florence d'Alché-Buc.
  Kernelizing the Output of Tree-Based Methods. ICML 2006.
  proposed by Razvan

• Michael Fink, Shai Shalev-Shwartz, Yoram Singer, Shimon Ullman.
  Online Multiclass Learning by Interclass Hypothesis Sharing. ICML 2006.
  proposed by Razvan
  
  
  
  

• T. Joachims. A Support Vector Method for Multivariate Performance Measures .ICML-05 (received best paper award).
  proposed by Misha, voted by Razvan

• N. Ireson, F. Ciravegna, M. Califf, D. Freitag, N. Kushmerick & A. Lavelli. Evaluating Machine Learning for Information Extraction .ICML-05.
  proposed by Misha

• S. Siddiqi & A. Moore. Fast Inference and Learning in Large-State-Space HMMs .ICML-05.
  proposed by Misha

• R. Madsen, D. Kauchak & C. Elkan. Modeling Word Burstiness Using the Dirichlet Distribution .ICML-05.
  proposed by Misha, voted by Razvan

• S. Kok & P. Domingos. Learning the Structure of Markov Logic Networks .ICML-05.
  proposed by Razvan

• Jure Leskovec, Jon Kleinberg & Christos Faloutsos. Graphs Over Time: Densification Laws, Shrinking Diameters, and Possible Explanations .KDD-05 (received best research paper award).
  proposed by Prem

• Hal Daume III & Daniel Marcu. Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction . ICML-05
  proposed by Razvan

• Jenny Rose Finkel, Trond Grenager & Christopher Manning. Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling . ACL-05
  proposed by Ray

• Charles Sutton & Andrew McCallum. Piecewise Training for Undirected Models . UAI-05
  (Efficiently train a large graphical model in separately normalized pieces, and amazingly often obtain higher accuracy than without this approximation. This paper also shows that this piecewise objective is a lower bound on the exact likelihood, and gives results with three different graphical model structures.)
  proposed by Razvan

• Niels Landwehr , Kristian Kersting & Luc De Raedt. nFOIL: Integrating Naive Bayes and FOIL . AAAI-05
  proposed by Lily

• Sanjoy Dasgupta Coarse sample complexity bounds for active learning . NIPS-05
  proposed by Razvan

• Avrim Blum Towards a more intuitive theory of Learning with Similarity Functions . Invited talk at the "Theoretical Foundations of Clustering" workshop, NIPS, 2005
  Related working paper: On a Theory of Kernels as Similarity Functions. Nina Balcan and Avrim Blum.
  proposed by Razvan
  
  
  
  

• B. Zadrozny. Learning and Evaluating Classifiers under Sample Selection Bias. ICML-04.

• H. Nguyen & A. Smeulders. Active Learning Using Pre-clustering. ICML-04.

• K. Brinker. Active Learning of Label Ranking Functions. ICML-04.

• R. Caruana, A. Niculescu-Mizil, G. >Crew & A. Ksikes. Ensemble Selection from Libraries of Models. ICML-04.

• A. Popescu, O. Etzioni & H. Kautz. Towards a Theory of Natural Language Interfaces to Databases. IUI-03.

• A. Popescu, A. Armanasu & O. Etzioni. Modern Natural Language Interfaces to Databases: Composing Statistical Parsing with Semantic Tractability. COLING-04.

• J. Goodman. Exponential Priors for Maximum Entropy Models. NAACL-04.

• G. Andrew, T. Grenager & C. Manning. Verb Sense and Subcategorization: Using Joint Inference to Improve Performance on Complementary Tasks. EMNLP-04.

• Y. Altun, T. Hofman & A. Smola. Gaussian Process Classification for Segmenting and Annotating Sequences. ICML-04.

• K. Toutanova, C. Manning & A. Ng. Learning Random Walks for Inducing Word Dependency Distributions. ICML-04.

• B. Taskar, C. Guestrin & D. Koller. Max-Margin Markov Networks. NIPS-04.

• B. Taskar, P. Abbeel & D. Koller.Discriminative Probabilistic Models for Relational Data. UAI-02.

• F. Sha & F. Pereira . Shallow Parsing with Conditional Random Fields. NAACL-03.

• M. Collins . Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. EMNLP-02.

• C. Anderson, P. Domingos & D. Weld. Relational Markov Models and their Application to Adaptive Web Navigation. KDD-02.

• R. Ghani, Combining Labeled and Unlabeled Data for MultiClass Text Categorization. ICML-02.

• I. Muslea, S. Minton & C. Knoblock. Active + Semi-supervised Learning = Robust Multi-View Learning. ICML-02.

• S. Sarawagi & A. Bhamidipaty, Interactive Deduplication using Active Learning, KDD-02.

• C. Aggarwal. A Human-Computer Co-operative System for Effective High Dimensional Clustering. KDD-01.

• C. Clarke, G. Cormack  & T. Lynam. Exploiting Redundancy in Question Answering.  SIGIR-01.

• A. Demiriz & K. Bennett. Optimization Approaches to Semi-supervised Learning. ICCP-99.

• W. Du Mouchell, & D. Pregibon. Empirical Bayes Screening For Multi-Item Associations In Massive Datasets. KDD-01.

• R. El-Yaniv & O. Souroujon. Iterative Double Clustering for Unsupervised and Semi-supervised Learning. ECML-01.

• M. Franz, S. McCarley, T. Ward & W. Zhu. Unsupervised and Supervised Clustering for Topic Tracking. SIGIR-01.

• A. Garg & D. Roth.. Understanding Probabilistic Classifiers. ECML-01.

• M. Halkidi, Y. Batistakis & M. Vazirgiannis. On Clustering Validation Techniques. To appear in Intelligent Information Systems Journal

• T. Joachims. A Statistical Learning Model of Text Classification for Support Vector Machines. SIGIR-01.

• Y. Yang. A Study on Thresholding Strategies for Text Categorization. SIGIR-01.

Subscribe to Email List

Subscribe to UT Machine Learning Group

Email:

For more information, please contact David Chen
Last Update: 09/06/2007