Tutorials for Machine Learning on Graphs

[IJCNN 2021] Unified Spatio-Temporal modeling for traffic forecasting using Graph Convolutional Network

Research Project I completed under Dr Vinti Agrawal at BITS Pilani.

Data and code for Salesforce Research paper, GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning - https://arxiv.org/abs/2012.03900 . The paper provides methods for constraint graph augmentation and optimal facility placement problems

A modular, accelerator-ready machine learning framework built in Go that speaks float8/16/32/64. Designed with clean architecture, strong typing, and native concurrency for scalable, production-ready AI systems. Ideal for engineers who value simplicity, speed, and maintainability.

A Task-Oriented graph SAmpler for HGNN

CLEVR graph: A dataset for graph based reasoning

An implementation of the paper "Deteksi Fraud Pinjaman P2P Lending Berbasis Graph Machine Learning untuk Kemandirian Teknologi" for Data Mining Division in GEMASTIK XVIII

Machine learning on graphs

Compare LLM text embeddings with structure-aware Graph AI (GNN link prediction) on any dataset with nodes, text, and edges.

Production-grade AML intelligence platform combining Graph ML, XGBoost, and LLMs with explainability and local deployment.

Self-Supervised Similarity Learning of Floor Layouts

Use NetworkViz to visualize IP Traffic flow as Graph ML problem

LaTeX research writing repo with structured build workflow and supporting artifacts.

A deep learning architecture combining spectral graph neural networks with curriculum learning for HOMO-LUMO gap prediction on PCQM4Mv2. Features a dual-view architecture with Chebyshev polynomial-based spectral convolutions and complexity-driven training schedules.

Production-grade Graph-RAG for Customer Journey Intelligence using NetworkX + LLM. Path-aware retrieval outperforming vector RAG on temporal queries, cohort comparison with real statistics, 5 pre-built analytics queries, and fully dockerized FastAPI/Streamlit architecture deployed on HuggingFace Spaces.

Graph representation learning — reproducing and analyzing core methods for academic study

A deep learning approach for molecular property prediction that introduces hierarchical attention pooling to capture scaffold-aware representations. The model aggregates atom features within functional groups before global pooling, combined with scaffold-based curriculum learning for improved generalization across diverse chemical structures.