Heterogeneous Graph Alignment for Joint Reasoning and Interpretability
This work addresses a significant problem in multi-graph learning for domains like neuroscience, offering a scalable and interpretable solution, though it appears incremental as it builds on existing Graph Transformer methods.
The paper tackled the challenge of integrating information across heterogeneous graphs with differing topologies and semantics, presenting the Multi-Graph Meta-Transformer (MGMT) framework that consistently outperforms state-of-the-art models in graph-level prediction tasks while providing interpretable representations.
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.