← Back to writing

Series

graph-theory-and-high-order-networks

5 parts, in order.

  1. 01

    Jul 10, 2026

    Revisiting the 2009 GNN Paper: Implementation (Part 2)

    How the 2009 GNN model actually works: the state update and output functions, the two-phase learning algorithm, the training flow, and the linear vs nonlinear transition functions.

  2. 02

    Jul 9, 2026

    Revisiting the 2009 GNN Paper: Foundations (Part 1)

    The theory behind Scarselli et al.'s original GNN paper: the tau function, information diffusion, universal approximation, and the positional/non-positional distinction.

  3. 03

    Nov 6, 2025

    What is a Hypergraph vs. a Regular (Relational) Graph?

    Why hypergraphs are the promised representation for learning networks — higher-order relationships, spatial context, and why HyGNN beats plain GCN.

  4. 04

    Sep 17, 2025

    When Graphs Meet Medicine: The Computational Revolution in Drug Interaction Prediction

    How graph and hypergraph neural networks turned drug interaction prediction from empirical guesswork into a computational discipline — and the cold-start problem still holding it back.

  5. 05

    Feb 9, 2025

    Graph Laplacian: From Basic Concepts to Modern Applications

    How one matrix bridges discrete graphs and continuous math — Laplacian smoothing, spectral analysis, and why GNNs depend on it.