NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation
This addresses the need for interpretable graph generation in domains like molecular design and knowledge graphs, offering an incremental improvement over existing methods by integrating topic modeling concepts.
The paper tackles the problem of limited interpretability in graph generation by proposing NGTM, a neural graph topic model that represents graphs as mixtures of latent topics over substructures, achieving competitive generation quality while enabling fine-grained control and interpretability.
Graph generation plays a pivotal role across numerous domains, including molecular design and knowledge graph construction. Although existing methods achieve considerable success in generating realistic graphs, their interpretability remains limited, often obscuring the rationale behind structural decisions. To address this challenge, we propose the Neural Graph Topic Model (NGTM), a novel generative framework inspired by topic modeling in natural language processing. NGTM represents graphs as mixtures of latent topics, each defining a distribution over semantically meaningful substructures, which facilitates explicit interpretability at both local and global scales. The generation process transparently integrates these topic distributions with a global structural variable, enabling clear semantic tracing of each generated graph. Experiments demonstrate that NGTM achieves competitive generation quality while uniquely enabling fine-grained control and interpretability, allowing users to tune structural features or induce biological properties through topic-level adjustments.