Instructors: Prof. Dr. Nassir Navab, Anees Kazi, Roger Soberanis, Mahsa Ghorbani

Announcements

  • 13.12.2021 - The recorded video of the first lecture has been added to the schedule.
  • 22.10.2021 - The schedule has been released.
  • 13.10.2021 - Let us know your four preferred papers by email by Sun. 17.10
  • 13.10.2021 - List of topics has been published. 
  • 12.10.2021 - The list of papers will be published on October 13th. Further details will be sent to the participants via email. 
  • 12.10.2021 - The classes will start on November 2nd, 12:00 pm - 2 pm CET. 
  • 15.07.2021 - Registrations are open from 15.07.2021 to 20.07.2021 through the TUM Matching Platform. Additionally, let us know your interest through our application form.
  • 12.07.2021 - The slides of the preliminary meeting are available here (slides).
  • 05.07.2021 - Course Wiki is up!
  • 05.07.2021 - Contact information. If you have any questions about the seminar, feel free to contact Roger Soberanis (roger.soberanis@tum.de) or Anees Kazi (anees.kazi@tum.de)

Introduction 

Graph Deep Learning is a new exotic branch in many fields like computer Vision and Medical Imaging. Many real-world medical and non-medical datasets can be represented in the form of graphs, providing a powerful source of information for machine learning models. This graph-based data, combined with the success of the convolutional neural networks, has motivated to translate the key ingredients of deep learning models into the graph domain. Many communities such as healthcare, social media, and computer vision are moving towards analyzing the data using Graph Convolutions. This seminar provides a space for discussion of the recent scientific publications on GCN with a focus on their medical applications and others.

Registration 

  • Interested students should attend the introductory meeting on 07.07.2021 to enlist in the course. Details are available at TUM online. 
  • Students can only register through TUM Matching Platform themselves if the maximum number of participants hasn't been reached (please pay attention to the Deadlines).
  • A maximum number of participants: 20.

Requirements and Course Structure

For this course, previous background in Machine/Deep Learning is required. 

During the course, students will select and present a scientific publication from the given list. Additionally, students will also contribute to the course blog post with their own summary of the selected article. Requirements are described in the image below: 

List of Topics

TopicNumberTitleJournal/ConferenceTutorStudentLink







Registration and reconstruction2GraphRegNet: Deep Graph Regularisation Networks on Sparse Keypoints for Dense Registration of 3D Lung CTsTMI 2021FaridNicolas Peterhttps://ieeexplore.ieee.org/abstract/document/9406964
Registration and reconstruction3Image-to-Graph Convolutional Network for Deformable Shape Reconstruction from a Single Projection Image.MICCAI 2021MahdiStella Dimitrahttps://arxiv.org/pdf/2108.12533.pdf
Registration and reconstruction4Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human PoseECCV 2020LennartDominikhttps://arxiv.org/pdf/2008.09047.pdf
Interpretability5INTERPRETING GRAPH NEURAL NETWORKS FOR NLP WITH DIFFERENTIABLE EDGE MASKINGICLR 2021 open reviewYousefJingpeihttps://openreview.net/forum?id=WznmQa42ZAx
Interpretability6Should Graph Convolution Trust Neighbors? A Simple Causal Inference MethodSigir 2021AshkanArminhttps://dl.acm.org/doi/pdf/10.1145/3404835.3462971
Interpretability7Disentangled Graph Convolutional NetworksInternational Conference on Machine Learning. PMLR, 2019AzadeAhmed Alaaeldin Fathy Hanafyhttp://proceedings.mlr.press/v97/ma19a/ma19a.pdf
General8Multi-label zero-shot learning with graph convolutional networksNeural Networks 2020

Alaa

Mohamed Taiebhttps://www.sciencedirect.com/science/article/abs/pii/S0893608020303336
General9Learning Graph Convolutional Networks for Multi-Label Recognition and ApplicationsTPAMI 2021MahsaSimayhttps://ieeexplore.ieee.org/abstract/document/9369105
Medical - Brain10BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisMedIA 2021

Shahrooz

Aminehttps://www.biorxiv.org/content/10.1101/2020.05.16.100057v4.full.pdf
Medical - Brain11Attention-Guided Deep Graph Neural Network for Longitudinal Alzheimer’s Disease AnalysisMICCAI 2020MathiasSergeihttps://link.springer.com/chapter/10.1007/978-3-030-59728-3_38
Medical - Brain12A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivityTMI 2021

Shahrooz

Nicolas Robert Baptistehttps://ieeexplore.ieee.org/abstract/document/9324801
Medical - Brain13Multi-Head GAGNN: A Multi-Head Guided Attention Graph Neural Network for Modeling Spatio-Temporal Patterns of Holistic Brain Functional NetworksMICCAI 2021AneesEreklehttps://link.springer.com/chapter/10.1007%2F978-3-030-87234-2_53
Medical - Segmentation and Classification14SGNET: Structure-Aware Graph-Based Networks for Airway Semantic SegmentationMICCAI 2021RogerJanikhttps://link.springer.com/chapter/10.1007%2F978-3-030-87193-2_15
Medical - Segmentation and Classification15Hybrid graph convolutional neural networks for landmark-based anatomical segmentationMICCAI 2021TariqFaridhttps://arxiv.org/abs/2106.09832
Medical - Segmentation and Classification16Early Detection of Liver Fibrosis Using Graph Convolutional NetworksMICCAI 2021MahsaSenerhttps://link.springer.com/chapter/10.1007/978-3-030-87237-3_21


Schedule


Sessions will take place Tuesdays from 12:00 to 14:00 hrs. A group of Two to Three students will present their papers during each session. 

The schedule will be released on 19.10. Sessions will start on 02.11 with introductory lectures by the organizers.

Place will be confirmed during the week of 25 of October.

DateTimePlaceTopicTutor (email)
StudentAdditional Info/ slides
2.11.2112:00 - 14:00
Intro to GDLMA I

Video Lecture
9.11.2112:00 - 14:00
Intro to GDLMA II


16.11.21

12:00 - 14:00


GraphRegNet: Deep Graph Regularisation Networks on Sparse Keypoints for Dense Registration of 3D Lung CTsFarid (mf.azampour@gmail.com)Nicolas Peter
Image-to-Graph Convolutional Network for Deformable Shape Reconstruction from a Single Projection Image.Mahdi (m.saleh@tum.de)Stella Dimitra
Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human PoseLennart (lennart.bastian@tum.de)Dominik

23.11.21

12:00 - 14:00






Project presentation by CAMP: Graph Deep Learning for Healthcare Applications.Dr. Anees Kazi





30.11.21

12:00 - 14:00


INTERPRETING GRAPH NEURAL NETWORKS FOR NLP WITH DIFFERENTIABLE EDGE MASKINGYousef (ashkan.khakzar@tum.de )Jingpei
Should Graph Convolution Trust Neighbors? A Simple Causal Inference MethodAshkan (ashkan.khakzar@tum.de )Armin
Disentangled Graph Convolutional NetworksAzade (azade.farshad@tum.de )Ahmed Alaaeldin Fathy Hanafy

7.12.21

12:00 - 14:00






Project presentation by CAMPDr. Hendrik Burwinkel





14.12.21

12:00 - 14:00


Multi-label zero-shot learning with graph convolutional networksAlaa / Anees (anees.kazi@tum.de)Mohamed Taieb
Learning Graph Convolutional Networks for Multi-Label Recognition and ApplicationsMahsa (mahsa.ghorbani@tum.de)Simay
BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisShahrooz (hahrooz.faghihroohi@tum.de)Amine

21.12.21

12:00 - 14:00






Project presentation by CAMP






28.12.21

12:00 - 14:00






No Session






4.01.22

12:00 - 14:00






No Session






11.01.22

12:00 - 14:00


Attention-Guided Deep Graph Neural Network for Longitudinal Alzheimer’s Disease AnalysisMathias (matthias.keicher@tum.de)Sergei
A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivityShahrooz (hahrooz.faghihroohi|[at]|tum.de)Nicolas Robert Baptiste
Multi-Head GAGNN: A Multi-Head Guided Attention Graph Neural Network for Modeling Spatio-Temporal Patterns of Holistic Brain Functional NetworksAnees (anees.kazi@tum.de)Erekle

18.01.22

12:00 - 14:00






Project presentation by CAMP






25.01.22

12:00 - 14:00


SGNET: Structure-Aware Graph-Based Networks for Airway Semantic SegmentationRoger (roger.soberanis@tum.de)Janik
Hybrid graph convolutional neural networks for landmark-based anatomical segmentationTariq (t.bdair@tum.de)Farid
Early Detection of Liver Fibrosis Using Graph Convolutional NetworksMahsa (mahsa.ghorbani@tum.de)Sener

1.02.21

12:00 - 14:00






Project presentation by CAMP






Resources and Material

An introductory lecture to GCNs by Prof. Xavier Bresson on Alfredo Canziani Youtube channel:


If you find more interesting material you would like to share in this section, feel free to contact us. 

  • Keine Stichwörter