Julien Ah-Pine (research)

⚀ The research domains in which I have general interest encompass:

• Statistics, Operational research, Optimization.
• Data science, Machine learning, Artificial intelligence.
• Complex data analysis: text, image, graph, high-dimensional, functional.
• Information fusion from mutlisource, multiview, multimedia, mixed data.
• Preference modeling, voting systems, social choice theory.
• Braid and knot invariants.

⚁ My current research activites focus on machine learning and optimization, functional data analysis, manifold learning and aggregation functions. Below are some related working papers:

• On using derivatives and multiple kernel methods for clustering and classifying functional data. [under review]
• Learning fuzzy measures and Choquet Integrals with a block coordinate descent approach.

⚂ Here are some talks that illustrate my research works:

• Talk at CMStatistics 2019 on: A study of the manifold hypothesis for functional data by using spectral clustering. [slides]
• Talk at the LISC seminar in 2019 on: An Efficient and Effective Generic Agglomerative Hierarchical Clustering Approach. [slides]
• Talk at the LIMOS seminar in 2017 on: Analyse Relationnelle Mathématique et ses applications en aide multicritère à la décision et en classification automatique. [slides]
• Talk at SFC 2017 on: Sur la normalisation de la matrice Laplacienne en partitionnement spectral. [slides]
• Talk at ADT 2013 on: Identification of a 2-additive bi-capacity by using mathematical programming. [slides]
• Talk at AMR 2009 on: A Continuum between Serendipitous Browsing and Query-based Search for Multimedia Information Access: [slides]

⚃ I participated in the following national and international research projects:

• 2014-2017 : Request -PIA-FSN- (Task leader): Big data analytics, Smart transports, Cybersecurity.
• 2011-2012 : DocNet -BQR Lyon 2- (Project leader): Integrated social and semantic network for scholars in humanities.
• 2009-2010 : SYNC3 -FP7-ICT-: Joint analysis and structuration of the news events and the blogosphere content.
• 2005-2009 : Infom@gic -Pôle de compétitivité Cap Digital-: Multimedia information processing, analysis, retrieval and mining.

⚄ I was co-advisor of the Phd work of:

• Edmundo Pavel Soriano Morales. Hypergraphs and Information Fusion for Term Representation Enrichment. Applications to Named Entity Recognition and Word Sense Disambiguation". Thèse de l'université de Lyon 2 defended in february 2018. Co-advised with Sabine Loudcher. Pavel is now at Etalab.
• Xinyu Wang. Toward Scalable Hierarchical Clustering and Co-clustering Methods: Application to the Cluster Hypothesis in Information Retrieval. Thèse de l'université de Lyon 2 defended in november 2017. Co-advised with Jérôme Darmont. Xinyu is now at Philips Research.

⚅ Below is the list of my publications (see also my Google Scholar profile). The preprints are available either on this website or on the HAL server:

2022

• Julien Ah-Pine. Learning doubly stochastic and nearly idempotent affinity matrix for graph-based clustering European Journal of Operational Research, 299(3): 1069-1078, 2022. [hal][ejor]
• Julien Ah-Pine and Noé Lebreton. Fusion tardive en analyse de données fonctionnelles élastiques. In 53ème Journées de Statistiques, JDS 2022.

2021

• Julien Ah-Pine. Sur l'apprentissage d'une matrice d'affinité bistochastique en clustering. In 52ème Journées de Statistiques, JDS 2021.
• Julien Ah-Pine and Anne-Françoise Yao. Multiple kernel SVM for classifying functional data in Sobolev spaces, Journées MAS 2020.

2020

• Julien Ah-Pine and Anne-Françoise Yao. Une approche par noyaux multiples pour l’apprentissage non-supervisé de représentation de données fonctionnelles dans des espaces de Sobolev. In 51ème Journées de Statistiques, JDS 2020. [paper]

2019

• Julien Ah-Pine and Anne-Françoise Yao. A study of the manifold hypothesis for functional data by using spectral clustering. 12th International Conference of the ERCIM WG on Computational and Methodological Statistics, CMStatistics 2019, London, UK, 14-16 December 2019. [slides]

2018

• Julien Ah-Pine. An Efficient and Effective Generic Agglomerative Hierarchical Clustering Approach. Journal of Machine Learning Research, 19(42), 2018. [hal][jmlr]

2017

• Edmundo-Pavel Soriano-Morales, Julien Ah-Pine, Sabine Loudcher. Fusion Techniques for Named Entity Recognition and Word Sense Induction and Disambiguation. Discovery Science - 20th International Conference, DS 2017, Kyoto, Japan, October 15-17, 2017, Proceedings. [hal]
• Xinyu Wang, Julien Ah-Pine, and Jérôme Darmont. SHCoClust, a scalable similarity-based hierarchical co-clustering method and its application to textual collections. In 2017 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2017, Naples, Italy, July 9-12, 2017, 2017. [hal]
• Julien Ah-Pine. Sur la normalisation de la matrice Laplacienne en partitionnement spectral. SFC 2017. [hal]
• Julien Ah-Pine, Xinyu Wang. Classification ascendante hiérarchique à noyaux et une application aux données textuelles. EGC 2017: 405-410. [hal]
• Xinyu Wang, Julien Ah-Pine, Jérôme Darmont. A New Test of Cluster Hypothesis Using a Scalable Similarity-Based Agglomerative Hierarchical Clustering Framework. CORIA 2017: 445-454 [hal]

2016

• Julien Ah-Pine. On aggregation functions based on linguistically quantified propositions and finitely additive set functions. Fuzzy Sets and Systems, 287:1–21, 2016. [hal]
• Edmundo-Pavel Soriano-Morales, Julien Ah-Pine, and Sabine Loudcher. Using a heterogeneous linguistic network for word sense induction and disambiguation. Computación y Sistemas, 20(3):315–325, 2016. [hal]
• Julien Ah-Pine and Xinyu Wang. Similarity based hierarchical clustering with an application to text collections. In Advances in Intelligent Data Analysis XV - 15th International Symposium, IDA 2016, Stockholm, Sweden, October 13-15, 2016, Proceedings, pages 320–331, 2016. [hal]
• Julien Ah-Pine and Edmundo-Pavel Soriano-Morales. A study of synthetic oversampling for twitter imbalanced sentiment analysis. In Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing, DMNLP 2016, co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD 2016, Riva del Garda, Italy, September 23, 2016., pages 17–24, 2016. [hal]
• Edmundo-Pavel Soriano-Morales, Julien Ah-Pine, and Sabine Loudcher. Hypergraph modelization of a syntactically annotated english wikipedia dump. In Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016, Portorož, Slovenia, May 23-28, 2016., 2016. [hal]

2015

• Julien Ah-Pine, Gabriela Csurka, and Stéphane Clinchant. Unsupervised visual and textual information fusion in CBMIR using graph-based methods. ACM Trans. Inf. Syst., 33(2):9:1–9:31, 2015. [hal]
• Antoine Rolland, Julien Ah-Pine, and Brice Mayag. Elicitation of 2-additive bi-capacity parameters. EURO Journal on Decision Processes, 3(1-2):5–28, 2015. [paper]
• Julien Ah-Pine and Xinyu Wang. Classification ascendante hiérarchique à noyaux et pistes pour un meilleur passage à léchelle. In 47ème Journées de Statistiques, JDS 2015. [hal]

2013

• Julien Ah-Pine. Graph clustering by maximizing statistical association measures. In Advances in Intelligent Data Analysis XII - 12th International Symposium, IDA 2013, London, UK, October 17-19, 2013. Proceedings, pages 56–67, 2013. [hal]
• Julien Ah-Pine, Brice Mayag, and Antoine Rolland. Identification of a 2-additive bi-capacity by using mathematical programming. In Algorithmic Decision Theory - Third International Conference, ADT 2013, Bruxelles, Belgium, November 12-14, 2013, Proceedings, pages 15–29, 2013. [hal]
• Julien Ah-Pine. A general framework for comparing heterogeneous binary relations. In Geometric Science of Information - First International Conference, GSI 2013, Paris, France, August 28-30, 2013. Proceedings, pages 188–195, 2013. [hal]

2012

• Brice Mayag, Antoine Rolland, and Julien Ah-Pine. Elicitation of a 2-additive bi-capacity through cardinal information on trinary actions. In Advances in Computational Intelligence - 14th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2012, Catania, Italy, July 9-13, 2012, Proceedings, Part IV, pages 238–247, 2012. [hal]

2011

• Julien Ah-Pine. On data fusion in information retrieval using different aggregation operators. Web Intelligence and Agent Systems, 9(1):43–55, 2011. [hal]
• Stéphane Clinchant, Julien Ah-Pine, and Gabriela Csurka. Semantic combination of textual and visual information in multimedia retrieval. In Proceedings of the 1st International Conference on Multimedia Retrieval, ICMR 2011, Trento, Italy, April 18 - 20, 2011, page 44, 2011. [hal]

2010

• Julien Ah-Pine and Jean-Franois Marcotorchino. Unifying some association criteria between partitions by using relational matrices. Communications in Statistics - Theory and Methods, 39(3):531 – 542, 2010. [hal]
• Julien Ah-Pine. On aggregating binary relations using 0-1 integer linear programming. In International Symposium on Artificial Intelligence and Mathematics, ISAIM 2010, Fort Lauderdale, Florida, USA, January 6-8, 2010, 2010. [hal]
• Julien Ah-Pine. Normalized kernels as similarity indices. In Advances in Knowledge Discovery and Data Mining, 14th Pacific-Asia Conference, PAKDD 2010, Hyderabad, India, June 21-24, 2010. Proceedings. Part II, pages 362–373, 2010. [hal]
• Julien Ah-Pine, Stéphane Clinchant, Gabriela Csurka, Florent Perronnin, and Jean-Michel Renders. Leveraging image, text and cross-media similarities for diversity-focused multimedia retrieval. In ImageCLEF, Experimental Evaluation in Visual Information Retrieval, pages 315–342. 2010. [hal]
• Julien Ah-Pine and Jean-Francois Marcotorchino. Overview of the relational analysis approach in data-mining and multi-criteria decision making. In Zeeshan ul-hassan Usmani PhD (Ed.), editor, Web Intelligence and Intelligent Agents. INTECH, 2010. [hal]
• Stéphane Clinchant, Gabriela Csurka, Julien Ah-Pine, Guillaume Jacquet, Florent Perronnin, Jorge Sánchez, and Keyvan Minoukadeh. Xrce's participation in wikipedia retrieval, medical image modality classification and ad-hoc retrieval tasks of imageclef 2010. In CLEF 2010 LABs and Workshops, Notebook Papers, 22-23 September 2010, Padua, Italy, 2010. [hal]
• Julien Ah-Pine. Une famille d’indices de similarité généralisant la mesure de cosinus. In Les XVIIes rencontres de la Société Francophone de Classification (SFC), SFC 2010, Saint-Denis de la Réunion, 9 - 11 Juin 2010. Actes, 2010. [hal]

2009

• Julien Ah-Pine, Marco Bressan, Stéphane Clinchant, Gabriela Csurka, Yves Hoppenot, and Jean-Michel Renders. Crossing textual and visual content in different application scenarios. Multimedia Tools Appl., 42(1):31–56, 2009. [hal]
• Julien Ah-Pine, Stéphane Clinchant, and Gabriela Csurka. Comparison of several combinations of multimodal and diversity seeking methods for multimedia retrieval. In Multilingual Information Access Evaluation II. Multimedia Experiments - 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009, Corfu, Greece, September 30 - October 2, 2009, Revised Selected Papers, pages 124–132, 2009. [hal]
• Julien Ah-Pine and Guillaume Jacquet. Clique-based clustering for improving named entity recognition systems. In EACL 2009, 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, Athens, Greece, March 30 - April 3, 2009, pages 51–59, 2009. [hal]
• Julien Ah-Pine. Cluster analysis based on the central tendency deviation principle. In Advanced Data Mining and Applications, 5th International Conference, ADMA 2009, Beijing, China, August 17-19, 2009. Proceedings, pages 5–18, 2009. [hal]
• Julien Ah-Pine, Jean-Michel Renders, and Marie-Luce Viaud. A continuum between browsing and query-based search for user-centered multimedia information access. In Adaptive Multimedia Retrieval. Understanding Media and Adapting to the User - 7th International Workshop, AMR 2009, Madrid, Spain, September 24-25, 2009, Revised Selected Papers, pages 111–123, 2009. [hal]
• Julien Ah-Pine, Stéphane Clinchant, Gabriela Csurka, and Yan Liu. Xrce's participation in Imageclef 2009. In Working Notes for CLEF 2009 Workshop co-located with the 13th European Conference on Digital Libraries (ECDL 2009) , Corfù, Greece, September 30 - October 2, 2009., 2009. [hal]

2008

• Julien Ah-Pine. Data fusion in information retrieval using consensus aggregation operators. In 2008 IEEE / WIC / ACM International Conference on Web Intelligence, WI 2008, 9-12 December 2008, Sydney, NSW, Australia, Main Conference Proceedings, pages 662–668, 2008. [hal]
• Julien Ah-Pine, Gabriela Csurka, and Jean-Michel Renders. Evaluation of diversity-focused strategies for multimedia retrieval. In Evaluating Systems for Multilingual and Multimodal Information Access, 9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008, Aarhus, Denmark, September 17-19, 2008, Revised Selected Papers, pages 677–684, 2008. [hal]
• Julien Ah-Pine, Claudio Cifarelli, Stéphane Clinchant, Gabriela Csurka, and Jean-Michel Renders. Xrce's participation to imageclef 2008. In Working Notes for CLEF 2008 Workshop co-located with the 12th European Conference on Digital Libraries (ECDL 2008) , Aarhus, Denmark, September 17-19, 2008. [hal]

Before 2008

• J. Ah-Pine and J-F Marcotorchino. Statistical, geometrical and logical independences between categorical variables. In Applied Stochastic Models and Data Analysis (ASMDA), Proceedings of the Conference, Chania Crete, 2007, 2007. [hal]
• J. Lemoine, H. Benhadda, and J. Ah-Pine. Classification non supervisée de documents hétérogènes : application au corpus 20 newsgroup. In Information Processing and Management of Uncertainty (IPMU), Proceedings of the Conference, 2006. [hal]
• J. Ah-Pine, J. Lemoine, and H. Benhadda. Un nouvel outil de classification non supervisée de documents pour la découverte de connaissances et la détection de signaux faibles : Rares text. In Colloque Ile Rousse, Les systmes d’information labore, 2005. [hal]

Phd thesis

• J. Ah-Pine. Sur des aspects algébriques et combinatoires de l'analyse relationnelle. Applications en classification automatique, en théorie du choix social et en théorie des tresses. Thèse de doctorat de l'université Pierre et Marie Curie, Paris VI.
  Membres du jury: P. Deheuvels (président), P. Cazes (rapporteur), I.C. Lerman (rapporteur), J.F. Marcotorchino (directeur), Y. Bennani (examinateur), J. Mairesse (examinateur), G. Saporta (examinateur). [hal][slides]

Master thesis

• J. Ah-Pine. Etudes des incertitudes lors de calculs de risques d’inondations : modélisations des erreurs dans les Modèles Numériques de Terrain.
  Stage recherche effectué à l'Institut Géographique National (IGN), équipe COGIT (Conception Objet et Généralisation de l’Information Topographique) et encadré par O. Bonin.