Autoencoders and Graph Autoencoders
Understand autoencoders through encoding, latent representations, and reconstruction, then see how graph autoencoders use GNNs to learn node attributes and graph structure.
01 GRAPH MACHINE LEARNING / RESEARCH NOTES
Exploring graph machine learning, unpacking papers, and documenting technology that is genuinely useful.
LATEST RELEASES
Understand autoencoders through encoding, latent representations, and reconstruction, then see how graph autoencoders use GNNs to learn node attributes and graph structure.
A two-step workflow for Obsidian users: constrain GPT with a fixed LaTeX prompt, then ask Codex to clean up formula formatting.
An introduction to graph neural networks through graph structure, neighborhood aggregation, message passing, and the shared logic behind GCN, GraphSAGE, and GAT.
A practical SEO guide for personal blogs and static sites, covering page metadata, sitemaps, Google Search Console, indexing, structured data, and ongoing optimization.
A study of Chinese A-share manufacturing firms from 2012 to 2022, examining how ESG performance affects green innovation and the mediating role of financing constraints.
A practical migration guide covering Astro, Pages Functions, KV storage, the admin panel, custom domains, HTTPS, and deployment.
1 research notes
↗ 02 / FOUNDATIONFoundations2 introductory articles
↗ 03 / PRACTICEUseful tips4 technical guides
↗