Dexa/Kyle Polich

Graph Rewriting Explained

Adam explains the concept of graph rewriting, emphasizing its role in transforming graphs by adding or changing nodes and relationships. He illustrates this with a relatable example involving KFC, making complex ideas accessible. The discussion highlights the vast potential of applying neural networks to graph rewriting, suggesting limitless possibilities for data manipulation and analysis.

In this clip
From this podcast
Data Skeptic
Graph Transformations
Related Questions
- I'm thinking that classical or deep ML solutions have a flaw in that they cannot be extended. For example, if one builds a model and wants to introduce a new feature, typically the model has to be retrained from scratch. So, I'm considering building a Knowledge Graph using LLMs. This knowledge graph would have to include time-dependent data (for example, it should be able to retrieve the "current" President of the USA and also previous presidents if asked). I'm thinking this Knowledge Graph could be used for Retrieval Augmented Generation (RAG) to help with business goals or maybe used with more clever User Interfaces (UIs). I'm not sure how to build or populate this KG and also have a rough idea of how to use it. Can you help me with suggesting particular paths for building and populating this Knowledge Graph?