| 
 
 Maysam Behmanesh
About me
I am a Postdoctoral Researcher in the  GeomeriX group  at the LIX research laboratory  of École Polytechnique IP-Paris, since April 2022, working with Prof. Maks Ovsjanikov. My current research focuses on machine learning, particularly geometric deep learning, with an emphasis on graphs and multimodal data.
 
I earned my PhD in Computer Engineering-Artificial Intelligence from the University of Isfahan (UI), where I conducted research in the ILS-Lab under the supervision of  Prof. Peyman Adibi. My doctoral research concentrated on geometric multimodal learning, leveraging the geometric structure of data for multimodal manifold learning and applying geometric deep learning to graph multimodal data. A part of my PhD research was completed at GIPSA-Lab in Grenoble Institute of Technology, Grenoble, where I was a visiting resercher under the supervision of Prof. Jocelyn Chanussot from 2019 to 2020.
 
Previously, I have worked on various topics, including chaotic time-series prediction, imbalanced data classification, neuro-fuzzy inference systems, and evolutionary computation. 
News
    November, 2024: 
     I gave a talk at Inria Paris, hosted by the   Argo research team. My talk was on "Enhancing Graph Neural Networks with Geometric Structure Analysis".
   Our new paper, Smoothed Graph Contrastive Learning via Seamless Proximity Integration, with Maks Ovsjanikov has been accepted at  Learning on Graphs Conference LoG-2024  PDF.
June, 2024:  
 
    Our new paper, Cross-Modal and Multimodal Data Analysis Based on Functional Mapping of Spectral Descriptors and Manifold Regularization, with Peyman Adibi, Jocelyn Chanussot and Sayyed Mohammad Saeed Ehsani is published in Neurocomputing , PDF.
    March, 2024:  
  I gave a talk at Télécom Paris, hosted by the  S2A team. My talk was on "Graph Representation Learning for Multimodal Data - Challenges and Innovative Methods". 
    April, 2023: 
  Our paper "TIDE: Time Derivative Diffusion for Deep Learning on Graphs", with Maximilian Krahn and Maks Ovsjanikov has been accepted at  ICML 2023,  PDF.   
October, 2022: 
      Our paper, "Geometric Multimodal Deep Learning With Multiscaled Graph Wavelet Convolutional Network", joint with Peyman Adibi, Saeed Ehsani, and Jocelyn Chanussot, is published in IEEE Transactions on Neural Networks and Learning Systems,  PDF.  
archive>>
 |