🧬 Build and explore a minimal Quantum-Graph Neural Network for node classification, combining classical encoders with quantum circuits for enhanced insights.

🖊️ Implement a feedforward neural network from scratch to accurately classify handwritten digits using the MNIST dataset with pure NumPy.

🔍 Explore Graph Neural Networks for node classification and link prediction using PyTorch Geometric, validating models on Cora and PubMed datasets.

A distributed vector database that learns. Store embeddings, query with Cypher, scale horizontally with Raft consensus, and let the index improve itself through Graph Neural Networks.

🧬 Predict drug interactions with the open-source CYP3A4 system, essential for research, education, and enhancing patient safety in medication management.

Transform geospatial relations into graph representations designed for spatial network analysis and Graph Neural Networks (GNNs).

A hpc LLVM Pass extracting semantic Control-Data Flow Graphs (CDFG) from Intermediate Representation for Graph Neural Networks. Enables cross-language code retrieval and clone detection beyond token-based approaches.

Modern Grid Management System

[NeurIPS 2025] Association-Focused Path Aggregation for Graph Fraud Detection

Unified thermodynamic cosmology developed by Morten Magnusson — connecting energy flow, entropy, and structure across scales.

Gigantic Graph Learning (GiGL) Framework: Large-scale training and inference for Graph Neural Networks

An ML-first temporal graph of Bitcoin's complete on-chain fund flows.

A collection of machine learning & deep learning projects and notebooks — regression, classification, explainable AI, and NLP fine‑tuning experiments.

Transforming relational data into graph structures to improve GNN performance using PyTorch Geometric.

A Resource-Constrained Project Scheduling Agent (RCPSA) based on GNN, e-greedy DQN, and model-based planning

Supporting material for Academy Course DAT31050

Advanced Temporal Graph Neural Networks for Critical Node Detection and Network Resilience Analysis

GraphSAGE + XGBoost ensemble for DNS malware detection. Achieved 97.43% accuracy on 200K-domain Zenodo dataset. Internship project.

A graph neural network for the segmentation and object detection in radar point clouds.

The integration of HugeGraph with AI/LLM & GraphRAG