Reading group on graphs

This reading group happens on Thursdays (usually at 2pm, but check the times) in room 101 of the INRIA building. If you know of some papers on graphs that you would like to add and present send me an email (gemma dot garriga at inria dot fr).

Next meetings

24/05/2012, 2pm: We will discuss the paper Revisiting k-means: New Algorithms via Bayesian Nonparametrics by Brian Kulis and Michael Jordan. Presented by David Chatel.
16/05/2012, 2pm: We will discuss the paper Latent spaces approaches to social networks by Hoff, P.D., Raftery, A.E., and Handcock, M.S. Presented by Antonino Freno.
26/04/2012, 2pm: We will discuss the paper A unified view of Kernel k-means, Spectral clustering and graph cuts by I.Dhillon, Y.Guan and B.Kulis. Presented by David Chatel.
12/01/2012, 11am: Complex output learning with kernels: from functional to structured data by Hachem Kadri. Room W11.
08/12/2011, 2pm: Tutorial on Hadoop by Teresa Klatzer.
01/12/2011, 2pm: We will discuss the paper Maximizing the spread of influence through a social network by D.Kempe, J.Kleinberg and E.Tardos. Presented by Gemma Garriga.
10/11/2011, 2pm: We will continue the discussion of the previous week on graph-based semi-supervised learning for structured tagging models, by Marc Tommasi and Pascal Denis.
04/11/2011, 11am: We will discuss the papers: Benefits of bias: towards better characterization of network sampling by Maiya and Berger-Wolf; presented by Remi Gilleron. Efficient graph-based semi-supervised learning of structured tagging models by Subramanya, Petrov and Pereira; presented by Marc Tommasi and Pascal Denis.
20/10/2011, 2pm: Michal Valko will present results from his Thesis Adaptive graph-based algorithms for conditional anomaly detection and semi-supervised learning. Room W11.
29/09/2011, 2pm: We will discuss the following papers: Predicting Thread Discourse Structure over Technical Web Forums, by L.Wang et al, at 2011 Conference on Empirical Methods in Natural Language Processing. Presented by Pascal Denis.
15/09/2011, 9am: We will discuss the following papers: Pseudolikelihood Estimation for Social Networks, by D. Strauss, M.Ikeda, at Journal of the American Statistical Association, 1990; and Recent developments in exponential random graph (p*) models for social networks by Garry Robins and Tom Snijders and Peng Wang and Mark Handcock, at Social Networks, 2006. Presented by Antonino Freno.
08/09/2011, 2pm: We will discuss the paper On node classification in dynamic content-based networks, by C. Aggarwal and N. Li. Presented by Remi Gilleron.
14/04/2011, 2pm: We will discuss the paper Learning with Hypergraphs: Clustering, Classification and Embedding by Zhou et al. Presented by Thomas Ricatte.
07/04/2011, 2pm: We will discuss results and tutorial on graph spectral clustering and spectra of graph, basic material from A tutorial on spectral clustering. Presented by Gemma Garriga.
10/03/2011, 2pm We will continue the discussion of the paper from last week. Presented by Mikaela Keller.
3/03/2011, 2pm: We will discuss the paper Link propagation: a fast semi-supervised learning algorithm for link prediction. Presented by Mikaela Keller.
17/02/2011, 2pm: We will discuss the paper on Factorizing Personalized Markov Chains for Next-Basket recommendations by Rendle, Freudenthaler and Schmidt-Thieme, WWW 2010. Presented by Jeremie Mary.
10/02/2011, 2pm: We will discuss graph construction methods for semi-supervised learning algorithms from the papers Large graph construction for scalable semi-supervised learning ICML 2010, and Graph construction and b-matching for semi-supervised learning ICML 2009. Presented by Gemma Garriga.
27/01/2011, 2pm: We will discuss current open problems of machine learning on graphs and the current collaborations with industry in the subject of machine learning.
20/01/2011, 2pm: We will discuss the ICML tutorial on Modeling Social and Information Networks: Opportunities for Machine Learning, by Jure Leskovec. It is necessary to have seen the tutorial at videolectures before. Presented by Marc Tommasi.
09/12/2010, 2pm: We will discuss the paper Kronecker graphs: an approach to modeling networks by Leskovec, Chakrabarti, Kleinberg, Faloutsos and Ghahramani. Presented by Marc Tommasi.
02/122010, 2pm: We will discuss the papers Sampling from large graphs and Sampling and estimation of network graphs. Presented by Gemma Garriga.
25/10/2010, 2pm We will discuss the second part of the paper from the previous week. Presented by Antoine Ndione.
18/10/2010, 2pm We will discuss the paper Property testing and its connection to learning and approximation. Presented by Antoine Ndione
04/10/2010, 2pm Kick-off meeting

Reading list

Network models and statistics


Testing properties on graphs

Streaming on graphs

Machine learning and applications on graphs

Link prediction

Other interesting links