Graph Data Modeling

Maciej discusses the integration of graph neural networks with rich data sets, emphasizing the importance of categorizing vertices and applying key-value pairs for enhanced modeling. He introduces LPG2VEC, an encoder that transforms diverse data into embeddings, allowing for seamless use across various graph neural network models. The conversation highlights the versatility of these methods across multiple domains, particularly in biological and social networks.

In this clip
From this podcast
Data Skeptic
Graphs for HPC and LLMs
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?

Graph Data Modeling

In this clip

From this podcast

Data Skeptic

Graphs for HPC and LLMs

Related Questions