Skip to content
View ZeinabRahbar's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report ZeinabRahbar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ZeinabRahbar/README.md

πŸ‘‹ Hi, I'm Zeinab Rahbar

AI Researcher | M.Sc. in Artificial Intelligence | Graph Neural Networks & Geometric Deep Learning

I am an AI researcher with a strong background in graph neural networks, latent graph structure learning, and multimodal representation learning. My work focuses on learning graph topologies from non-graph data and understanding how information propagates through learned structuresβ€”with applications in healthcare and biomedical AI.

πŸ”¬ I am actively seeking Research positions in Graph Machine Learning, Geometric Deep Learning, and Multimodal AI for Healthcare. If your lab works on:

  • Graph Neural Networks & Geometric Deep Learning
  • Graph representation learning / Latent graph structure learning
  • Multimodal learning for biomedical applications

... let's talk.

πŸ“§ Email: ZeinabRahbar2022@gmail.com
🌐 Website: zeinabrahbar.github.io
πŸ”— LinkedIn: linkedin.com/in/zeinab-rahbar


πŸ“š Research Interests

  • Graph Neural Networks (GNNs)
  • Geometric Deep Learning
  • Graph Representation Learning & Latent Graph Structure Learning
  • Multimodal Learning (text, vision, clinical data)
  • AI for Healthcare & Biomedical Data

🧠 Thesis & Selected Projects

πŸŽ“ M.Sc. Thesis – Learning Latent Graph Structures for Multimodal Text and Vision Tasks

  • Developed differentiable latent graph structure learning frameworks for multimodal data
  • Applied to disease prediction (TADPOLE / Alzheimer's, ABIDE / Autism) achieving best reported results on ABIDE
  • Extended to Visual Question Answering (VQA v2.0) – the first graph-level structure learning approach for VQA
  • Supervised by Dr. Peyman Adibi (University of Isfahan) & Dr. Alireza Darvishy (ZHAW, Switzerland)

πŸ”¬ Selected Projects

  • Graph Convolutional Networks with Random Weights – Independent PyTorch implementation of the IEEE TPAMI 2023 paper. No public code was available at the time – I built it from scratch.
    πŸ”— View Repository β†’

  • GNN-based Visual Question Answering – Investigated graph structure learning for relational reasoning on VQA v2.0


πŸ’Ό Experience

Role Organization Period
Machine Vision Engineer HoopadVision Feb 2024 – Mar 2025
Python Instructor Yasan Academy 2023 – 2024
Teaching Assistant – Machine Learning University of Isfahan (Dr. Adibi) 2022 – 2025
Teaching Assistant – Computer Basics University of Isfahan (Dr. Ehsani) 2022 – 2025
Teaching Assistant – Discrete Mathematics Arak University (Dr. Amiri) 2022

πŸŽ“ Education

  • M.Sc. in Computer Engineering (Artificial Intelligence) – University of Isfahan (2022–2025)
  • B.Sc. in Computer Engineering – Arak University (2018–2022)

πŸ› οΈ Technical Skills

Category Technologies
Languages Python, C++
Deep Learning PyTorch, TensorFlow, PyTorch Geometric (PyG), DGL
Scientific Computing NumPy, scikit-learn, Pandas, Matplotlib
Tools & Deployment Docker, Git, Linux, FastAPI, VS Code
Languages Persian (Native), English (IELTS 7.0), French (A1)

πŸ“« Get in Touch

I'm open to research collaborations and PhD opportunities. Feel free to reach out:

πŸ“§ Email: ZeinabRahbar2022@gmail.com
🌐 Website: zeinabrahbar.github.io
πŸ”— LinkedIn: linkedin.com/in/zeinab-rahbar
πŸ™ GitHub: github.com/ZeinabRahbar


β€œI study how to learn the hidden graph structure connecting multimodal data β€” text, images, and clinical measurements β€” instead of assuming a fixed one, so models can propagate information the way the underlying system actually works.”

Pinned Loading

  1. GCNRW-Graph-Convolutional-Network-With-Random-Weights- GCNRW-Graph-Convolutional-Network-With-Random-Weights- Public

    Here is an implementation of Title: "Are Graph Convolutional Networks With Random Weights Feasible?" Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence Year: 2023

    Jupyter Notebook 5

  2. Implementation-for-the-paper-of-SEMI-SUPERVISED-CLASSIFICATION-WITH-GRAPH-CONVOLUTIONAL-NETWORKS Implementation-for-the-paper-of-SEMI-SUPERVISED-CLASSIFICATION-WITH-GRAPH-CONVOLUTIONAL-NETWORKS Public

    This ia a simple implementation of SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS on three datasets(Cora, PubMed and Citeseer) and inspecting changing the first layer activation f…

    Jupyter Notebook 1