Heterogeneous Graph Alignment for Joint Reasoning and Interpretability

TL;DR

The paper introduces MGMT, a scalable and interpretable framework for joint reasoning across heterogeneous graphs, effectively aligning and integrating information without shared node identities, demonstrated on synthetic and neuroscience data.

Contribution

It proposes a novel Meta-Graph Transformer that unifies multi-graph learning, enabling cross-graph reasoning and interpretability in heterogeneous graph collections.

Findings

MGMT outperforms state-of-the-art models in graph-level prediction tasks.

Provides interpretable insights through supernodes and superedges.

Effective on both synthetic and real-world neuroscience datasets.

Abstract

Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of shared node identities, remains a significant challenge. We present the Multi-Graph Meta-Transformer (MGMT), a unified, scalable, and interpretable framework for cross-graph learning. MGMT first applies Graph Transformer encoders to each graph, mapping structure and attributes into a shared latent space. It then selects task-relevant supernodes via attention and builds a meta-graph that connects functionally aligned supernodes across graphs using similarity in the latent space. Additional Graph Transformer layers on this meta-graph enable joint reasoning over intra- and inter-graph structure. The meta-graph provides built-in interpretability: supernodes and superedges highlight influential substructures and cross-graph alignments. Evaluating MGMT on both synthetic datasets and real-world neuroscience applications, we show that MGMT consistently outperforms existing state-of-the-art models in graph-level prediction tasks while offering interpretable representations that facilitate scientific discoveries. Our work establishes MGMT as a unified framework for structured multi-graph learning, advancing representation techniques in domains where graph-based data plays a central role.