Machine Learning for Graph Data

Outline

  • Deep Learning for graph data
  • Machine Learning with kernel methods for graph data
  • Molecule synthesis by solving the pre-image problem for graph data
  • Machine Learning for online social networks : application to spam detection on Twitter

Deep Learning for graph data

Analyzing the expressive power of graph neural networks in a spectral perspective. Balcilar, M.; Renton, G.; Héroux, P.; Gaüzère, B.; Adam, S.; and Honeine, P. Submitted to Ninth International Conference on Learning Representations (ICLR 2021), Vienna, Austria, 4 – 7 May 2021.

When Spectral Domain Meets Spatial Domain in Graph Neural Networks. Balcilar, M.; Renton, G.; Héroux, P.; Gaüzère, B.; Adam, S.; and Honeine, P. In Proceedings of Thirty-seventh International Conference on Machine Learning (ICML 2020) – Workshop on Graph Representation Learning and Beyond (GRL+ 2020), Vienna, Austria, 12 – 18 July 2020.
[code] [paper] [presentationvideo]

Spectral-designed Depthwise Separable Graph Neural Networks. Balcilar, M.; Renton, G.; Héroux, P.; Gaüzère, B.; Adam, S.; and Honeine, P. In Proceedings of Thirty-seventh International Conference on Machine Learning (ICML 2020) – Workshop on Graph Representation Learning and Beyond (GRL+ 2020), Vienna, Austria, 12 – 18 July 2020.
[code] [paper] [presentationvideo]

Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks. Balcilar, M.; Renton, G.; Héroux, P.; Gaüzère, B.; Adam, S.; and Honeine, P. Technical Report HAL Normandie Université, 2020.
[code] [link] [paper]

Machine Learning with kernel methods for graph data

Graph Kernels based on Linear Patterns: Theoretical and Experimental Comparisons. Jia, L.; Gaüzère, B.; and Honeine, P. In Preprints : hal-02053946.
[paper]

Graph Kernels based on Linear Patterns: Theoretical and Experimental Comparisons. Jia, L.; Gaüzère, B.; and Honeine, P. In Poster presented at the Machine Learning Summer School, Universidad Autonoma de Madrid, Madrid, Spain, 27 August – 7 September 2018.

A Metric Learning Approach to Graph Edit Costs for Regression. Jia, L.; Gaüzère, B.; Yger, F.; and Honeine, P. In Proceedings of the IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (S+SSPR), Venice, Italy, 21 – 22 January 2021.

Molecule synthesis by solving the pre-image problem for graph data

A Graph Pre-image Method Based on Graph Edit Distances. Jia, L.; Gaüzère, B.; and Honeine, P. In Proceedings of the IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (S+SSPR), Venice, Italy, 21 – 22 January 2021

See also :
A Metric Learning Approach to Graph Edit Costs for Regression. Jia, L.; Gaüzère, B.; Yger, F.; and Honeine, P. In Proceedings of the IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (S+SSPR), Venice, Italy, 21 – 22 January 2021.

Machine Learning for online social networks : application to spam detection on Twitter

SimilCatch: Enhanced Social Spammers Detection on Twitter using Markov Random Fields. El-Mawass, N.; Honeine, P.; and Vercouter, L. Information Processing and Management, 57(6): 102317. 2020.
[link] [paper][doi]

Supervised Classification of Social Spammers using a Similarity-based Markov Random Field Approach. El-Mawass, N.; Honeine, P.; and Vercouter, L. In Proc. the 5th multidisciplinary international social networks conference, of MISNC ’18, pages 14:1 – 14:8, New York, NY, USA, 16 – 18 July 2018. ACM 
[link] [paper] [doi]

Champ Aléatoire de Markov pour la Détection Supervisée des Comptes Malicieux sur Twitter. El-Mawass, N.; Honeine, P.; and Vercouter, L. In 20-ème Conférence d’Apprentissage automatique (CAp) – 20th annual meeting of the francophone Machine Learning community, Rouen, France, 20 – 22 June 2018. 
[paper]