SurrealDB 3.0 wants to replace your five-database RAG stack with one

SurrealDB 3.0 launches with $23M in new funding and a pitch to replace multi-database RAG stacks with a single engine that handles vectors, graphs, and agent memory transactionally.
IEEE

When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning

Abstract: Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has ...
GitHub

SQL-Mongo Converter - A Lightweight SQL to MongoDB (and Vice Versa) Query Converter

SQL-Mongo Converter is a lightweight Python library for converting SQL queries into MongoDB query dictionaries and converting MongoDB query dictionaries into SQL statements. It is designed for ...
IEEE

Wasserstein Graph Neural Networks for Graphs With Missing Attributes

Abstract: Missing node attributes pose a common problem in real-world graphs, impacting the performance of graph neural networks’ representation learning. Existing GNNs often struggle to effectively ...