Instructors: Prof. Dr. Nassir Navab, Anees Kazi, Roger Soberanis, Mahsa Ghorbani
- 26.04.2021 - Access details for the course are available in the course Moodle.
- 12.04.2021 - Assignments have been released! Check the date for your presentation and contact your tutor on time.
- 06.04.2021 - [Optional] Let us know your four preferred papers by email before Fri. 09.04
- 06.04.2021 - List of topics has been published.
- 12.02.2021 - Registrations are open from 11.02.2021 to 16.02.2021 through the TUM Matching Platform. Additionally, let us know your interest through our application form.
- 03.02.2021 - Students interested in participating in the seminar should attend the preliminary meeting on Feb 08, 2021. 4:00 pm. Due to the pandemic situation, the meeting will be online.
- 03.02.2021 - Course Wiki is up!
- 02.02.2021 - Contact information. If you have any questions about the seminar, feel free to contact Roger Soberanis (firstname.lastname@example.org) or Anees Kazi (email@example.com)
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.
- Interested students should attend the introductory meeting to enlist in the course.
- 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
|1||Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson’s Disease||AMIA Annu Symp Proc. 2018||Shahrooz||Cizevskij||https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371363/|
|2||Cgc-net: Cell graph convolutional network for grading of colorectal cancer histology images||ICCV 2019||Ario||Hayran||http://openaccess.thecvf.com/content_ICCVW_2019/html/VRMI/Zhou_CGC-Net_Cell_Graph_Convolutional_Network_for_Grading_of_Colorectal_Cancer_ICCVW_2019_paper.html|
|3||Uncertainty-based Graph Convolutional Networks for Organ Segmentation Refinement||MIDL 2020||Timo||Khattab||http://proceedings.mlr.press/v121/soberanis-mukul20a/soberanis-mukul20a.pdf|
|4||Latent-Graph Learning for Disease Prediction||MICCAI 2020||Timo||Cuturilo||https://link.springer.com/chapter/10.1007/978-3-030-59713-9_62|
|5||A joint 3D UNet-Graph Neural Network-based method for Airway Segmentation from chest CT||MLMI 2019||Roger||Graf||https://www.springerprofessional.de/en/a-joint-3d-unet-graph-neural-network-based-method-for-airway-seg/17256006|
|6||Graph Random Neural Networks for Semi-Supervised Learning on Graphs||NeurIPS 2020||Mahsa||Imdahl||https://paperswithcode.com/paper/graph-random-neural-network|
|7||Recovering Brain Structural Connectivity from Functional Connectivity via Multi-GCN Based Generative Adversarial Network||MICCAI 2020||Roger||Ivarsson||https://papers.nips.cc/paper/2020/file/968c9b4f09cbb7d7925f38aea3484111-Paper.pdf|
|10||Temporal Graph Networks For Deep Learning on Dynamic Graphs||Shun-Cheng Wu||Bani-Harouni||https://arxiv.org/pdf/2006.10637.pdf|
|11||Graph Meta Learning via Local Subgraphs||NeurIPS 2020||Azade||Kayali||https://arxiv.org/pdf/2006.07889.pdf|
|12||Learning Graph Embeddings for Compositional Zero-shot Learning||CVPR 2021||Azade||Gabsi||https://arxiv.org/pdf/2102.01987.pdf|
Interpretability, Robustness, and Improving
|13||Simplifying Graph Convolutional Networks||ICML 2019||Anees||Müller||http://proceedings.mlr.press/v97/wu19e.html|
|14||Interpreting Graph Neural Networks For NLP With Differentiable Edge Masking||ICLR 2021||Anees||Kini||https://openreview.net/forum?id=WznmQa42ZAx|
|15||On The Bottleneck of Graph Neural Networks and Its Practical Implications||ICLR 2021||Ashkan||Kistol||https://openreview.net/forum?id=i80OPhOCVH2|
|16||Attacking Graph Convolutional Networks via Rewiring||ICLR 2021||Mehrdad||Kiesgen||https://openreview.net/forum?id=B1eXygBFPH|
|17||Distilling Knowledge from Graph Convolutional Networks||Mehrdad||Kadri||https://arxiv.org/pdf/2003.10477.pdf|
Sessions will take place Tuesdays from 12:00 to 14:00 hrs, in a virtual zoom meeting. A group of Two to Three students will present their papers during each session.
The list of papers will be published during the second half of March. You will receive an email for selecting your preferences. The list of assigned papers is planned to be available early in April.
On 27.04.2021, there will be an introductory lecture on Graph Deep Learning by the organizers. To keep a fair preparation time after this introductory session, the first group will have one week to finish their blogpost and two weeks for preparing their presentation after the introductory lecture.
Topics for each session to be announced.
Course Schedule (Tentative):
|08.02.2021||16:00-16:30||Zoom Meeting||Preliminary Meeting|
|05.04 - 09.04 2021||Papers assignments to be released (contact your corresponding tutor once you know your paper)|
|27.04.2021||12:00 - 14:00||Zoom Meeting||Intro to Graph Deep Learning|
|18.05.2021||12:00 - 14:00||Zoom Meeting|
|25.05.2021||12:00 - 14:00||Zoom Meeting|
|01.06.2021||12:00 - 14:00||Zoom Meeting|
|08.06.2021||12:00 - 14:00||Zoom Meeting|
|15.06.2021||12:00 - 14:00||Zoom Meeting|
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.