Symbolic Graph Intelligence: Hypervector Message Passing for Learning Graph-Level Patterns with Tsetlin Machines

TL;DR

This paper introduces a symbolic graph classification method using hypervector message passing and Tsetlin Machines, achieving competitive accuracy with enhanced interpretability over neural models.

Contribution

It presents a novel multilayered symbolic framework for graph classification that combines hypervector encoding with Tsetlin Machines, emphasizing interpretability and hierarchical semantic preservation.

Findings

Achieves competitive accuracy on TUDataset benchmarks.

Provides a local interpretability framework for graph classification.

Uses sparse binary hypervectors for efficient graph encoding.

Abstract

We propose a multilayered symbolic framework for general graph classification that leverages sparse binary hypervectors and Tsetlin Machines. Each graph is encoded through structured message passing, where node, edge, and attribute information are bound and bundled into a symbolic hypervector. This process preserves the hierarchical semantics of the graph through layered binding from node attributes to edge relations to structural roles resulting in a compact, discrete representation. We also formulate a local interpretability framework which lends itself to a key advantage of our approach being locally interpretable. We validate our method on TUDataset benchmarks, demonstrating competitive accuracy with strong symbolic transparency compared to neural graph models.