# TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning

arXiv: https://arxiv.org/abs/2006.11825 · HTML: https://mlsanity.com/paper/2006.11825/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [EventGPT: Event Stream Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2412.00832/) (2024)
- [Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2209.00654/) (2022)
- [TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting](https://mlsanity.com/paper/2511.18539/) (2025)
- [EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2103.02517/) (2021)
- [Revisiting 2D Convolutional Neural Networks for Graph-based Applications](https://mlsanity.com/paper/2105.11016/) (2021)
- [Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)](https://mlsanity.com/paper/2303.11169/) (2023)
- [Uncertainty Quantification via H"older Divergence for Multi-View Representation Learning](https://mlsanity.com/paper/2411.00826/) (2024)

## Abstract (arXiv)

General graphs are difficult for learning due to their irregular structures. Existing works employ message passing along graph edges to extract local patterns using customized graph kernels, but few of them are effective for the integration of such local patterns into global features. In contrast, in this paper we study the methods to transfer the graphs into trees so that explicit orders are learned to direct the feature integration from local to global. To this end, we apply the breadth first search (BFS) to construct trees from the graphs, which adds direction to the graph edges from the center node to the peripheral nodes. In addition, we proposed a novel projection scheme that transfer the trees to image representations, which is suitable for conventional convolution neural networks (CNNs) and recurrent neural networks (RNNs). To best learn the patterns from the graph-tree-images, we propose TreeRNN, a 2D RNN architecture that recurrently integrates the image pixels by rows and columns to help classify the graph categories. We evaluate the proposed method on several graph classification datasets, and manage to demonstrate comparable accuracy with the state-of-the-art on MUTAG, PTC-MR and NCI1 datasets.