Artificial Intelligence Research Seminar Artificial Intelligence Research Laboratory Fall 2004

Artificial Intelligence Research Seminar Com S 610 (VH, DM, JT) Fall 2004 will meet once a week on Thursdays from 12:30pm to 2:00pm in room 223, Atanasoff Hall. AI seminar will be coordinated by Vasant Honavar, Dimitris Margaritis, Jin Tian with help from Doina Caragea and Oksana Yakhnenko.

Place: 223 Atanasoff Hall

Time: 12:30pm to 2:00pm, Thursdays

Talk Schedule: TBA

The seminar will focus on probabilistic graphical models with special emphasis on statistical machine learning algorithms that can operate on topologically structured data (sequences, images, graphs, relational databases).

Organization

Each talk will be assigned to a team consisting of a discussion leader and 1-2 discussants. Each participant is expected to study the assigned readings well in advance of each week's seminar and come prepared to participate in the discussions. Each participant will be expected to lead the discussion at least once during the semester, and assume the role of the discussant at least 2 times during the semester.

The discussion leader should ideally motivate the topic, present the relevant background and context for the material being presented, organize and explain the main ideas and results, and discuss the relevance to research in our lab. Before you lead the discussion in a seminar, you should read and throroughly understandthe relevant background material, and the 2-3 papers that cover the topic being presented, and prepare slides / transparencies to organize thoughts and help the audience follow the material being presented.

The discussant(s) will assist the discussion leader in preparing for the seminar, review, critique, and help revise the materials, and be ready to step in and provide additional details, examples, clarifications, as needed during the seminar.

Focus Topics

Conditional Probability Models for Finite Systems of Spatially or Temporally Interacting Random Variables

(5 meetings)

Readings

• Lauritzen, S.L. (1996). Graphical Models. (Chapters 2 and 3 on Conditional Independence and Markov Models). London: Oxford University Press.

• Besag, J. (1974). Spatial Interaction and Statistical Analysis of Lattice Systems. Spatial Interaction and the Statistical Analysis of Lattic Systems. Journal of the Royal Statistical Society, Vol. 36, pp. 192-235, 1974.

• On the Statistical Analysis of Dirty Pictures, Julian Besag, Journal of the Royal Statistical Society B, vol. 48, 1986, pp. 259-302

• Boykov, Y., Veksler, O., and Zabih, R. (1998) Markov Random Fields with Efficient Approximations

• Shallow Parsing and Conditional Markov Fields Fei Sha and Fernando Pereira, 2003.

• Markov Random Fields and ApplicationsRoss Kindermann and Laurie Snell. 1980. American Mathematical Society.

• S. Kumar and M. Hebert (2003). Discriminative Fields for Modeling Spatial Dependencies in Natural Images In: Advances in Neural Information Processing Systems (NIPS), December 2003.

• Introduction to Conditional Random Fields.

• S. Geman and D. Geman. Stochastic relaxation, gibbs distributions and the bayesian restoration of images. IEEE Trans. PAMI, 6:721 - 741, 1984.

• Excerpt of Markov Random Field Modeling in Computer Vision, by S.Z. Li. Berlin: Springer-Verlag, 1995.

  Training Conditional Random Fields Via Gradient Tree Boosting T. Dietterich et al. 2004.

• Max-Margin Markov Networks, B. Taskar, C. Guestrin and D. Koller. To appear NIPS-2003.

• Parameter estimation for stochastic context-free graph grammars
  Tim Oates, Fang Huang, and Shailesh Doshi

Learning from Relational Data

(8 meetings)

Readings

• Jensen, D. Neville, J. and Hay, M. Avoiding Bias When Aggregating Relational Data With Degree Disparity Proceedings of the Twentieth International Conference on Machine Learning. 2003.

• Jensen, D. and J. Neville (2002). Autocorrelation and Linkage Cause Bias in Evaluation of Relational Learners. Proceedings of the 12th International Conference on Inductive Logic Programming.

• Jensen, D. and J. Neville (2002). Linkage and Autocorrelation Cause Feature Selection Bias in Relational Learning.Proceedings of the 19th International Conference on Machine Learning.

• Perlich, C. and Provost, F. Aggregation Based Feature Invention for Relational Learning
  Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2003.

• Probabilistic Models for Relational Data.
  D. Heckerman, C. Meek, and D. Koller. Technical Report MSR-TR-2004-30, Microsoft Research, March, 2004.

• Koller, D. Probabilistic Models of Relational Data

• Atramentov, A., Leiva, H., and Honavar, V. (2003). A Multi-Relational Decision Tree Learning Algorithm - Implementation and Experiments.. In: Proceedings of the Thirteenth International Conference on Inductive Logic Programming. Berlin: Springer-Verlag. In press.

• Relational Learning with Statistical Predicate Invention: Better Models for Hypertext.
  Mark Craven and Sean Slattery. Machine Learning, 43(1-2): 97-119, 2001.

• Learning Probabilistic Relational Models
  Lise Getoor, Nir Friedman, Daphne Koller and Avi Pfeffer
  (IJCAI'99 paper by same name and authors)
  

• The relational vector-space model and industry classification
  Abraham Bernstein, Scott Clearwater, and Foster Provost
  

  Discriminative probabilistic models for relational data
  Ben Taskar, Pieter Abbeel and Daphne Koller
  

• Categorizing unsupervised relational learning algorithms
  Hannah Blau and Amy McGovern
  

• Aggregation versus selection bias, and relational neural networks
  Hendrik Blockeel and Maurice Bruynooghe
  

• Feature extraction languages for propositionalized relational learning
  Chad Cumby and Dan Roth
  

• Individuals, relations and structures in probabilistic models
  James Cussens
  

• Operations for learning with graphical models
  Wray Buntine

  CLP(BN): Constraint Logic Programming for Probabilistic Knowledge
  Vitor Santos Costa, David Page, Maleeha Qazi and James Cussens (UAI'03)

  Learning Markov networks: Maximum bounded tree-width graphs (Symposium on Discrete Algorithms, 2001)
  David Karger and Nathan Srebro

  Ecosystem analysis using probabilistic relational modeling
  Bruce D'Ambrosio, Eric Altendorf, and Jane Jorgensen
  

• Research on statistical relational learning at the University of Washington
  Pedro Domingos, Yeuhi Abe, Corin Anderson, Anhai Doan, Dieter Fox, Alon Halevy, Geoff Hulten, Henry Kautz, Tessa Lau, Lin Liao, Jayant Madhavan, Mausam, Donald J. Patterson, Matthew Richardson, Sumit Sanghai, Daniel Weld and Steve Wolfman

  Relational learning for securities market regulation
  Henry Goldberg
  

• Social network relational vectors for anonymous identity matching
  Shawndra Hill
  

• Mining massive relational databases
  Geoff Hulten, Pedro Domingos, and Yeuhi Abe
  

• Representational power of probabilistic-logical models: From upgrading to downgrading
  Kristian Kersting
  

• Logical Markov decision programs
  Kristian Kersting and Luc De Raedt
  

• First-order probabilistic models for information extraction
  Bhaskara Marthi, Brian Milch, and Stuart Russell
  

• A Note on the unification of information extraction and data mining using conditional-probability, relational models
  Andrew McCallum and David Jensen
  

• Statistical relational learning: Four claims and a survey
  Jennifer Neville, Matthew Rattigan, and David Jensen
  

• Aggregation and concept complexity in relational learning
  Claudia Perlich and Foster Provost
  

  Aggregation-based feature invention and relational concept classes
  Claudia Perlich and Foster Provost
  

  Relational learning problems and simple models
  Foster Provost, Claudia Perlich and Sofus Macskassy
  

• Neville, J., D. Jensen, L. Friedland and M. Hay (2003). Learning Relational Probability Trees. Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

• Neville, J., D. Jensen and B. Gallagher (2003). Simple Estimators for Relational Bayesian Classifers. Proceedings of The Third IEEE International Conference on Data Mining .

• Statistical Relational Learning for Link Prediction. Alexandrin Popescul, Lyle H. Ungar , Workshop on Learning Statistical Models from Relational Data at IJCAI 2003.

• A comparison of stochastic logic programs and Bayesian logic programs
  Aymeric Puech and Stephen Muggleton
  

  Principles of Learning Bayesian Logic Programs
  Kristian Kersting and Luc De Raedt

  Learning statistical models of time-varying relational data
  Sumit Sanghai, Pedro Domingos and Daniel Weld

• Relational learning: A web-page classification viewpoint
  Sean Slattery

• Statistical modeling of graph and network data
  Padhraic Smyth
  

  Label and link prediction in relational data
  Ben Taskar, Pieter Abbeel, Ming-Fai Wong, and Daphne Koller
  

  Toward a high-performance system for symbolic and statistical modeling
  Neng-Fa Zhou, Taisuke Sato, and Koiti Hasidad
  

For additions and updates to this page, please contact: honavar@cs.iastate.edu.

Artificial Intelligence Research Laboratory
Computational Intelligence, Learning, and Discovery Program
Department of Computer Science
Iowa State University
Atanasoff Hall, Ames, IA 50011-1040 USA
phone: +1-515-294-4377, fax: +1-515-294-0258