Danai Koutra is a Ph.D. candidate in the Computer Science Department at Carnegie Mellon University. Her research interests include large-scale graph mining, graph similarity and matching, graph summarization, and anomaly detection. Danai's research has been applied mainly to social, collaboration and web networks, as well as brain connectivity graphs. She holds one "rate-1" patent and has six (pending) patents on bipartite graph alignment. Danai has multiple papers in top data mining conferences, including 2 award-winning papers, and her work has been covered by the popular press, such as the MIT Technology Review. She has worked at IBM Hawthorne, Microsoft Research Redmond, and Technicolor Palo Alto/Los Altos. She earned her M.S. in Computer Science from CMU in 2013 and her diploma in Electrical and Computer Engineering at the National Technical University of Athens in 2010.


@article{ GatterbauerGKF14,
author= {Wolfgang Gatterbauer and
Stephan G{\"{u}}nnemann and
Danai Koutra and
Christos Faloutsos},
title = {{Linearized and Single-Pass Belief Propagation}},
journal   = {{PVLDB}},
year  = {2014},
volume= {8},
issue = {4},
note  = {{To be presented at the 41st International Conference on Very
Large Data Bases, August 31st - September 4th, 2015, Kohala
Coast, Hawaii}}
}

@inproceedings{ LaseckiGKJDB14,
author= {Walter S. Lasecki and
Mitchell Gordon and
Danai Koutra and
Malte F. Jung and
Steven P. Dow and
Jeffrey P. Bigham},
title = {Glance: rapidly coding behavioral video with the crowd},
booktitle = {The 27th Annual {ACM} Symposium on User Interface Software
and Technology, {UIST} '14, Honolulu, HI, USA, October 5-8, 2014},
year  = {2014},
pages = {551--562},
}

@InProceedings{	KoutraBH14_TAIA,
author= {Danai Koutra and
Paul N. Bennett and
Eric Horvitz},
title = {Influences of a Shocking News Event on Information Seeking},
journal   = {SIGIR 2014 Workshop on Temporal, Social and Spatially-aware
Information Access (TAIA)},
year  = {2014},
}

@inproceedings{DBLP:conf/pakdd/KangLKF14,
author= {U. Kang and
Jay Yoon Lee and
Danai Koutra and
Christos Faloutsos},
title = {Net-Ray: Visualizing and Mining Billion-Scale Graphs},
booktitle = {Advances in Knowledge Discovery and Data Mining - 18th
Pacific-Asia Conference, {PAKDD} 2014, Tainan, Taiwan,
May 13-16, 2014. Proceedings, Part {I}},year  = {2014},
pages = {348--361},
}

@inproceedings{ LinRLKRF14,
author= {Yibin Lin and
Agha Ali Raza and
Jay Yoon Lee and
Danai Koutra and
Roni Rosenfeld and
Christos Faloutsos},
title = {Influence Propagation: Patterns, Model and a Case Study},
booktitle = {Advances in Knowledge Discovery and Data Mining - 18th
Pacific-Asia Conference, {PAKDD} 2014, Tainan, Taiwan,
May 13-16, 2014. Proceedings, Part {I}},
year  = {2014},
pages = {386--397},
}

@inproceedings{ AraujoPGFBSPK14,
author= {Miguel Araujo and
Spiros Papadimitriou and
Stephan G{\"{u}}nnemann and
Christos Faloutsos and
Prithwish Basu and
Ananthram Swami and
Evangelos E. Papalexakis and
Danai Koutra},
title = {Com2: Fast Automatic Discovery of Temporal ('Comet') 
Communities},
booktitle = {Advances in Knowledge Discovery and Data Mining - 18th 
Pacific-Asia Conference, {PAKDD} 2014, Tainan, Taiwan, 
May 13-16, 2014. Proceedings, Part {II}},
year  = {2014},
pages = {271--283},
}

@article{ KoutraBH14,
author= {Danai Koutra and
Paul N. Bennett and
Eric Horvitz},
title = {Events and Controversies: Influences of a Shocking News Event 
on Information Seeking},
journal   = {CoRR},
year  = {2014},
volume= {abs/1405.1486},
url   = {http://arxiv.org/abs/1405.1486},
}

@article{ AkogluTK14,
author= {Leman Akoglu and
Hanghang Tong and
Danai Koutra},
title = {Graph-based Anomaly Detection and Description: {A} Survey},
journal   = {Data Mining and Knowledge Discovery (DAMI)},
year  = {2014},
volume= {28},
number= {4},
publisher = {Springer}
}

@inproceedings{ KoutraKVF14,
author= {Danai Koutra and
U. Kang and
Jilles Vreeken and
Christos Faloutsos},
title = {{VOG:} Summarizing and Understanding Large Graphs},
booktitle = {Proceedings of the 2014 {SIAM} International Conference on Data 
Mining, Philadelphia, Pennsylvania, USA, April 24-26, 2014},
year  = {2014},
pages = {91--99},
}

@PhDThesis{ Koutra14,
author	= {Koutra, Danai},
title   = {{Large Graph Mining and Sense-making}},
school	= {Computer Science Department, Carnegie Mellon University},
type= {Master Thesis},
year= {2014}
}

@inproceedings{ KoutraTL13,
author= {Danai Koutra and
Hanghang Tong and
David Lubensky},
title = {{BIG-ALIGN:} Fast Bipartite Graph Alignment},
booktitle = {2013 {IEEE} 13th International Conference on Data Mining, 
Dallas, TX, USA, December 7-10, 2013},
year  = {2013},
pages = {389--398},
}

@inproceedings{ BerlingerioKEF13,
author= {Michele Berlingerio and
Danai Koutra and
Tina Eliassi{-}Rad and
Christos Faloutsos},
title = {Network similarity via multiple social theories},
booktitle = {Advances in Social Networks Analysis and Mining 2013, 
{ASONAM} '13, Niagara, ON, Canada - August 25 - 29, 2013},
year  = {2013},
pages = {1439--1440},
}

@inproceedings{ Senator+13,
author= {Ted E. Senator and
Henry G. Goldberg and
Alex Memory and
William T. Young and
Brad Rees and
Robert Pierce and
Daniel Huang and
Matthew Reardon and
David A. Bader and
Edmond Chow and
Irfan A. Essa and
Joshua Jones and
Vinay Bettadapura and
Duen Horng Chau and
Oded Green and
Oguz Kaya and
Anita Zakrzewska and
Erica Briscoe and
Rudolph L. Mappus IV and
Robert McColl and
Lora Weiss and
Thomas G. Dietterich and
Alan Fern and
Weng{-}Keen Wong and
Shubhomoy Das and
Andrew Emmott and
Jed Irvine and
Jay Yoon Lee and
Danai Koutra and
Christos Faloutsos and
Daniel D. Corkill and
Lisa Friedland and
Amanda Gentzel and
David Jensen},
title = {Detecting insider threats in a real corporate database of 
computer usage activity},
booktitle = {The 19th {ACM} {SIGKDD} International Conference on Knowledge 
Discovery and Data Mining, {KDD} 2013, Chicago, IL, USA, 
August 11-14, 2013},
year  = {2013},
pages = {1393--1401},
}

@InProceedings{ KoutraYSRJC13,
author	= {Danai Koutra and
Yu Gong and
Sephira Ryman and
Rex Jung and
Joshua T. Vogelstein and
Christos Faloutsos},
title		= {Are all brains wired equally?},
booktitle	= {Organization for Human Brain Mapping (OHBM)},
year		= {2013}
}

@inproceedings{LeeKKF13,
author= {Jay Yoon Lee and
U. Kang and
Danai Koutra and
Christos Faloutsos},
title = {Fast anomaly detection despite the duplicates},
booktitle = {Proceedings of the 22nd International Conference on World 
Wide Web (WWW Companion Volume)},
year  = {2013},
pages = {195-196},
}

@inproceedings {KoutraVF13,
author= {Koutra, Danai and 
Vogelstein, Joshua and 
Faloutsos, Christos},
title = {{DeltaCon: A Principled Massive-Graph Similarity Function}},
booktitle = {Proceedings of the 13th SIAM International Conference on 
Data Mining (SDM)},
year  = {2013},
pages = {162-170},
}

@inproceedings{ KoutraKPF13,
author= {Danai Koutra and 
Vasileios Koutras and
B. Aditya Prakash and
Christos Faloutsos},
title = {{Patterns amongst Competing Task Frequencies: Super-Linearities,
and the Almond-DG Model}},
booktitle = {Proceedings of the 17th Pacific-Asia Conference on Knowledge 
Discovery and Data Mining (PAKDD)},
year  = {2013},
pages = {201-212},
}

@inproceedings{ BerlingerioKEF12nips,
author   = "Berlingerio, Michele and Koutra, Danai and Eliassi-Rad,
Tina and Faloutsos, Christos",
title= {{A Scalable Approach to Size-Independent Network Similarity}},
booktitle= "NIPS 2012, Workshop on Social Network and Social Media Analysis, 
Methods, Models, and Applications, Lake Tahoe, NV, USA",
month= "Dec",
year = "2012",
}

@InProceedings{	KoutraPF12,
author	= {Danai Koutra and Evangelos Papalexakis and Christos
Faloutsos},
title		= {{TENSORSPLAT: Spotting Latent Anomalies in Time}},
booktitle	= {16th Panhellenic Conference on Informatics (PCI)},
year		= {2012}
}

@inproceedings{ BerlingerioKEF12,
author   = "Berlingerio, Michele and Koutra, Danai and Eliassi-Rad,
Tina and Faloutsos, Christos",
title= {{NetSimile: A Scalable Approach to Size-Independent Network
Similarity}},
booktitle   = "WIN 2012, Workshop on Information in Networks",
month= "Sept",
year = "2012",
}

@inproceedings{ HendersonGETBAKFL12,
author= {Keith Henderson and
Brian Gallagher and
Tina Eliassi-Rad and
Hanghang Tong and
Sugato Basu and
Leman Akoglu and
Danai Koutra and
Christos Faloutsos and
Lei Li},
title = {{RolX: structural role extraction {\&} mining in large graphs}},
booktitle = {Proceedings of the 18th ACM International Conference on 
Knowledge Discovery and Data Mining (SIGKDD)},
year  = {2012},
pages = {1231-1239},
}

@inproceedings{ AkogluCKKF12,
author = {Akoglu, Leman and Chau, Duen Horng and Kang, U.
and Koutra, Danai and Faloutsos, Christos},
title = {{OPAvion: mining and visualization in large graphs}},
series = {Proceedings of the ACM International Conference on Management 
of Data (SIGMOD)},
year = {2012},
pages = {717--720},
publisher = {ACM},
}

@incollection {KoutraKKCPF11,
author = {Koutra, Danai and Ke, Tai-You and Kang, U. and 
Chau, Duen and Pao, Hsing-Kuo and Faloutsos, Christos},
title  = {{Unifying Guilt-by-Association Approaches:
Theorems and Fast Algorithms}},
booktitle = {Machine Learning and Knowledge Discovery in Databases 
(ECML/PKDD)},
series = {Lecture Notes in Computer Science},
pages  = {245-260},
volume = {6912},
year   = {2011}
}

@PhDThesis{ Koutra10,
author	= {Koutra, Danai},
title   = {{Approximate sequence matching with MapReduce}},
school	= {Electrical and Computer Engineering, 
National Technical University of Athens},
type= {Diploma Thesis},
year= {2010}
}

Danai Koutra pronounced:

fast algorithms for
understanding massive
graphs

Danai

Ph.D. Candidate
Computer Science Dept. (GHC 8023)
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA, 15213

E-mail: danai@cs.cmu.edu
Work: (+1) 412-268-3074

I am graduating in May 2015 and I am currently looking for academic / research positions!
CV | Research Statement | Teaching Statement


I develop fast algorithms for understanding massive graphs. My algorithms combine globality with locality to (a) assess the similarity between graphs or nodes, and (b) summarize graphs in terms of their important structures or underlying models. I am a Ph.D. Candidate in the Computer Science Department at Carnegie Mellon University advised by Professor Christos Faloutsos.

Research Interests: data mining, large-scale graph mining, graph similarity, graph matching, graph summarization and visualization, graph anomaly and event detection, applied machine learning


Selected publications (Full list)

Graph Summarization:

Danai Koutra, U Kang, Jilles Vreeken, Christos Faloutsos. VoG:Summarizing and Understanding Large Graphs. SDM 2014, Philadelphia, PA, April 2014.
Selected as one of the best papers of SDM'14.

Graph Alignment and Similarity

Danai Koutra, Hanghang Tong, David Lubensky. BIG-ALIGN: Fast Bipartite Graph Alignment. IEEE ICDM 2013, Dallas, TX, December 2013.

Danai Koutra, Joshua Vogelstein, Christos Faloutsos. DeltaCon: A Principled Massive-Graph Similarity Function. SDM 2013, Austin, TX, May 2013.

Node Similarity (Proximity)

Danai Koutra, Tai-You Ke, U Kang, Duen Horng (Polo) Chau, Hsing-Kuo Kenneth Pao, and Christos Faloutsos. Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms. ECML PKDD, Athens, Greece, Sep. 2011.


Tutorials

Node and graph similarity: Theory and Applications. With Tina Eliassi-Rad and Christos Faloutsos. IEEE ICDM 2014, Shenzen, China, December 2014. (acceptance ratio: 22%)

Node similarity, graph similarity and matching: Theory and Applications. With Tina Eliassi-Rad and Christos Faloutsos. SDM 2014, Philadelphia, PA, April 2014. (over 100 researchers attended!)


Selected projects

VoG: Summarizing and Understanding Large Graphs.

VoG

How can we succinctly describe a million-node graph with a few simple sentences? How can we measure the 'importance' of a set of discovered subgraphs in a large graph? Our main ideas are to construct a 'vocabulary' of subgraph-types that often occur in real graphs (e.g., stars, cliques, chains), and from a set of subgraphs, find the most succinct description of a graph in terms of this vocabulary.

Specifically, our first insight is to best describe the structures in a graph using an enriched set of 'vocabulary' terms: cliques and near-cliques (which are typically considered by community detection methods), and also stars, chains and (near) bi-partite cores. The second insight is to formalize our goal as a lossless compression problem, and use the MDL principle. The best summary of a graph is the set of subgraphs that describes the graph most succinctly, i.e., compresses it best, and, thus, helps a human understand the main graph characteristics in a simple, non-redundant manner. The proposed algorithm, VoG, has the following input and output.

Input: a graph
Output: a set of possibly overlapping subgraphs that most succinctly describe the given graph, i.e., that explain as many of its edges in as simple possible terms.

Publication: VoG: Summarizing and Understanding Large Graphs.
Project: Bridging HCI with data mining.
Code: vog.tar Updated!


DeltaCon: Similarity Function between Large Graphs.

DeltaCon

How much did a network change since yesterday? How different is the wiring between Bob's brain (a left-handed male) and Alice's brain (a right-handed female)? Graph similarity with known node correspondence, i.e. the detection of changes in the connectivity of graphs, arises in numerous settings, such as temporal anomaly detection and protein-protein interaction. DELTACON is a principled, intuitive, and scalable algorithm that assesses the similarity between two graphs on the same nodes (e.g. employees of a company, customers of a mobile carrier). It has the following inputs and outputs:

Input: (a) two graphs with same nodes and different edge sets
            (b) node correspondence
Output: similarity score s in [0,1], where 0 means completely
            dissimilar and 1 means identical

Publication: DeltaCon: A Principled Massive-Graph Similarity Function.
Project: Graph Similarity with Attribution and Alignment.
Code: deltacon.zip


Almond-DG: Distribution for competing tasks

Almond-DG

What is the appropriate 2-d distribution to fit real, 2-d points in social networks? For example, how can we model the joint distribution of the number of messages vs. number of phone-calls that each customer makes?

Almond-DG is our proposed digitized 2-d distribution which matches our empirical observation in real-world social networks: super-linear relationships among tasks (variables -- e.g., number of messages and number of phone-calls), and log-logistic marginals. This distribution uses copulas, a powerful technique, which has been successfully used in survival models, financial risk management, and decision analysis.

Publication: Patterns amongst Competing Task Frequencies: Super-Linearities, and the Almond-DG model.
Code: almonddg.tar


FaBP: Fast Belief Propagation for 2-label classification in networked data

FaBP

If several friends of Smith have committed petty thefts, what would you say about Smith? Guilt-by-association methods combine weak signals to derive stronger ones, and have been extensively used for anomaly detection and classification in numerous settings (e.g., accounting fraud, cyber-security, calling-card fraud). Network effects are very powerful, resulting even in popular proverbs like "birds of a feather flock together". In social networks, obese people tend to have obese friends, happy people tend to make their friends happy too, and in general, people usually associate with like-minded friends with respect to politics, hobbies, religion etc. Thus, knowing the types of a few nodes in a network, (say, "honest" vs "dishonest"), we would have good chances to guess the types of the rest of the nodes.

Among the most successful guilt-by-association techniques is Belief Propagation, for which there are no convergence guarantees in loopy networks (= typical real-world networks). The proposed algorithm, FaBP, is a fast approximation of Belief Propagation that yields 2x speedup, equal or higher accuracy, and is guaranteed to converge. The inputs, outputs and assumptions of the algorithm are briefly described below.

Input: graph with n nodes and m edges; and few labeled nodes (e.g., possible classes red/green)
Output: class (red/green) for the rest of the nodes
Assuming: network effects (homophily / heterophily)

Publication: Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms.
Project: Graph Similarity with Attribution and Alignment.
Code: fabp.zip


Scripts

heatmap Scatter Heatmap

Input: csv file with (x,y,value) triplets
Output: heatmap for scatter data in log-log scale


Code: heatmap.rar


1D and 2D distributions for a given a set of features

Input: tab-separated file with one observation
          per line (each column corresponds to a feature)
Output: the 1D distribution for each feature
            all the pairwise 2D distributions

Code: distributionPlots.zip


Setup hadoop and pegasus

Code: setEnv.sh


Publications

    2015
  1. Wolfgang Gatterbauer, Stephan Guennemann, Danai Koutra, Christos Faloutsos. Linearized and Single-Pass Belief Propagation. Proceedings of the VLDB Endowment, Volume 8(4) (VLDB'15), August 2015.
    [bibtex] [code]
    2014
  2. Walter S. Lasecki, Mitchell Gordon, Danai Koutra, Malte Jung, Steven P. Dow and Jeff P. Bigham. Glance: Rapidly Coding Behavioral Video with the Crowd. ACM Symposium on User Interface Science and Technology (UIST'14), October 2014.
    [bibtex]
  3. Danai Koutra, Paul N. Bennett, Eric Horvitz. Influences of a Shocking News Event on Web Browsing.SIGIR 2014 Workshop on Temporal, Social and Spatially-aware Information Access (TAIA'14), July 2014.
    [bibtex] [slides]
  4. U Kang, Jay-Yoon Lee, Danai Koutra, Christos Faloutsos. Net-Ray: Visualizing and Mining Web-Scale Graphs PAKDD 2014, Tainan, Taiwan, May 2014.
    [bibtex]
    Recipient of a travel award.
  5. Yibin Lin, Agha Ali Raza, Jay-Yoon Lee, Danai Koutra, Roni Rosenfeld, Christos Faloutsos. Influence Propagation: Patterns, Model and Case Study. PAKDD 2014, Tainan, Taiwan, May 2014.
    [bibtex] [slides]
  6. Miguel Araujo, Spiros Papadimitriou, Stephan Guennemann, Christos Faloutsos, Prithwish Basu, Ananthram Swami, Evangelos E. Papalexakis, Danai Koutra. Com2: Fast Automatic Discovery of Temporal (Comet) Communities. PAKDD 2014, Tainan, Taiwan, May 2014.
    [bibtex]
    Best student paper award (runner up).
  7. Danai Koutra, Paul N. Bennett, Eric Horvitz. Events and Controversies: Influences of a Shocking News Event on Information Seeking. arXiv:1405.1486, May 2014.
    [bibtex]
    News coverage (MIT Review, Technology.org).
  8. Leman Akoglu, Hanghang Tong, Danai Koutra. Graph-based Anomaly Detection and Description: A Survey. Data Mining and Knowledge Discovery (DAMI), April 2014.
    [bibtex]
  9. Danai Koutra, U Kang, Jilles Vreeken, Christos Faloutsos. VoG:Summarizing and Understanding Large Graphs. SDM 2014, Philadelphia, PA, April 2014.
    [bibtex] [slides][code] Updated!
    Selected as one of the best papers of SDM'14.
    Taught in graduate courses: Saarland University at the Dept. of Databases and Information Systems (TADA).
    Recipient of a travel award.
  10. Danai Koutra. Large Graph Mining and Sense-making. Thesis proposal, CMU, March 2014.
    [bibtex]
    2013
  11. Danai Koutra, Hanghang Tong, David Lubensky. BIG-ALIGN: Fast Bipartite Graph Alignment. IEEE ICDM 2013, Dallas, TX, December 2013.
    [bibtex] [slides]
    Recipient of a travel award.
  12. Michele Berlingerio, Danai Koutra, Tina Elliasi-Rad, Christos Faloutsos.Network Similarity via Multiple Social Theories. Proceedings of the 5th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013), Niagara Falls, Canada, August 2013.
    [bibtex]
  13. Ted Senator, Danai Koutra et al. Detecting Insider Threats in a Real Corporate Database of Computer Usage Activities. KDD 2013, Chicago, IL, August 2013.
    [bibtex]
  14. Danai Koutra, Yu Gong, Sephira Ryman, Rex Jung, Joshua Vogelstein, Christos Faloutsos. Are all brains wired equally? OHBM 2013, Seattle, WA, June 2013.
    [bibtex]
  15. Jay-Yoon Lee, U Kang, Danai Koutra, Christos Faloutsos. Fast anomaly detection despite the duplicates. WWW 2013, Rio de Janeiro, Brazil, May 2013. (poster)
    [bibtex]
  16. Danai Koutra, Joshua Vogelstein, Christos Faloutsos. DeltaCon: A Principled Massive-Graph Similarity Function. SDM 2013, Austin, Texas, May 2013.
    [bibtex] [slides] [code]
    Taught in graduate courses: Rutgers University (CS 16:198:672).
    Recipient of a travel award.
  17. Danai Koutra, Vasileios Koutras, B. Aditya Prakash, Christos Faloutsos. Patterns amongst Competing Task Frequencies: Super-Linearities, and the Almond-DG model.PAKDD 2013, Gold Coast, Queensland, Australia, April 2013.
    [bibtex] [slides]
    Taught in graduate courses: Virginia Tech (CS 6604).
    2012
  18. Michele Berlingerio, Danai Koutra, Tina Eliassi-Rad, Christos Faloutsos. A Scalable Approach to Size-Independent Network Similarity. NIPS 2012, Workshop on Social Network and Social Media Analysis, Methods, Models, and Applications, Lake Tahoe, NV, Dec. 2012.
    [bibtex] [poster]
  19. Danai Koutra, Evangelos Papalexakis, Christos Faloutsos. TENSORSPLAT: Spotting Latent Anomalies in Time. PCI (16th Panhellenic Conference on Informatics w/ international participation), Piraeus, Greece, Oct. 2012.
    [bibtex] [slides]
  20. Michele Berlingerio, Danai Koutra, Tina Eliassi-Rad, Christos Faloutsos. [NetSimile: A Scalable Approach to Size-Independent Network Similarity. WIN 2012, Workshop on Information in Networks, New York, NY, Sept. 2012. (presentation and panel discussion)
    [bibtex]
  21. Keith Henderson, Brian Gallagher, Tina Eliassi-Rad, Hanghang Tong, Sugato Basu, Leman Akoglu, Danai Koutra, Lei Li, Christos Faloutsos. RolX: Structural Role Extraction & Mining in Large Graphs. ACM SIGKDD, Beijing, China, Aug. 2012.
    [bibtex]
  22. Leman Akoglu*, Duen Horng Chau*, U Kang*, Danai Koutra*, and Christos Faloutsos. [Large Graph Mining System for Patterns, Anomalies & Visualization. 16th Pacific-Asia Conference, PAKDD 2012, Kuala Lumpur, Malaysia, May 2012. (demo, *: authors in alphabetical order)
    [bibtex]
  23. Leman Akoglu*, Duen Horng Chau*, U Kang*, Danai Koutra*, and Christos Faloutsos. OPAvion: Mining and visualization in large graphs. ACM SIGMOD Conference 2012, Scottsdale, Arizona, USA, May 2012. (demo paper, *: authors in alphabetical order)
    [bibtex]
    2011
  24. Danai Koutra, Tai-You Ke, U Kang, Duen Horng (Polo) Chau, Hsing-Kuo Kenneth Pao, and Christos Faloutsos. Unifying Guilt-by-Association Approaches: Theorems and Fast Algorithms. ECML PKDD, Athens, Greece, Sep. 2011.
    [bibtex][slides][code][poster]
    Taught in graduate courses: CMU at Tepper School of Business (47-953), Rutgers University (CS 16:198:672).

    2010
  25. Danai Koutra. Approximate sequence matching with MapReduce. Diploma Thesis, NTUA, Jul. 2010.
    [bibtex]slides]