Your Model Reads the Whole Database. What Counts as an Explanation?

This page did not load. You can still read it on the original site — the toolbar below keeps your place in the directory.

Relational deep learning runs models directly over multi-table databases, with no human-written joins. That convenience makes the models hard to explain. Two 2025-2026 papers take opposite shots at the problem: SQL views versus meta-paths. A look at whether the space has legs.

Read on neovintage.org ↗