# Graph Structural-topic Neural Network

arXiv: https://arxiv.org/abs/2006.14278 · HTML: https://mlsanity.com/paper/2006.14278/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 16 of 16)

- [Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2106.12931/) (2021)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels](https://mlsanity.com/paper/2104.02995/) (2021)
- [COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing](https://mlsanity.com/paper/2402.16424/) (2024)
- [Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective](https://mlsanity.com/paper/2402.13556/) (2024)
- [Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations](https://mlsanity.com/paper/2402.01231/) (2024)
- [GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation](https://mlsanity.com/paper/2407.12338/) (2024)
- [A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks](https://mlsanity.com/paper/2101.09300/) (2021)
- [Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction](https://mlsanity.com/paper/2105.07752/) (2021)
- [SA2GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation](https://mlsanity.com/paper/2512.07857/) (2025)
- [Graph Embedding with Hierarchical Attentive Membership](https://mlsanity.com/paper/2111.00604/) (2021)
- [Representation Learning on Heterostructures via Heterogeneous Anonymous Walks](https://mlsanity.com/paper/2201.06972/) (2022)
- [Towards Graph Prompt Learning: A Survey and Beyond](https://mlsanity.com/paper/2408.14520/) (2024)
- [Structure-Guided Input Graph for GNNs facing Heterophily](https://mlsanity.com/paper/2412.01757/) (2024)
- [CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials](https://mlsanity.com/paper/2508.15392/) (2025)
- [NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation](https://mlsanity.com/paper/2507.13133/) (2025)

## Abstract (arXiv)

Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes. However, commonly do GCNs focus more on node features but less on graph structures within the neighborhood, especially higher-order structural patterns. However, such local structural patterns are shown to be indicative of node properties in numerous fields. In addition, it is not just single patterns, but the distribution over all these patterns matter, because networks are complex and the neighborhood of each node consists of a mixture of various nodes and structural patterns. Correspondingly, in this paper, we propose Graph Structural-topic Neural Network, abbreviated GraphSTONE, a GCN model that utilizes topic models of graphs, such that the structural topics capture indicative graph structures broadly from a probabilistic aspect rather than merely a few structures. Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently. In addition, we design multi-view GCNs to unify node features and structural topic features and utilize structural topics to guide the aggregation. We evaluate our model through both quantitative and qualitative experiments, where our model exhibits promising performance, high efficiency, and clear interpretability.