# Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

arXiv: https://arxiv.org/abs/1904.04238 · HTML: https://mlsanity.com/paper/1904.04238/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2019.

## Built on by (most cited first, 13 of 13)

- [On Representation Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2111.04964/) (2021)
- [Debiased Graph Neural Networks with Agnostic Label Selection Bias](https://mlsanity.com/paper/2201.07708/) (2022)
- [Graph Kernel Neural Networks](https://mlsanity.com/paper/2112.07436/) (2021)
- [Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning](https://mlsanity.com/paper/2211.09155/) (2022)
- [Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation](https://mlsanity.com/paper/2107.00946/) (2021)
- [AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing](https://mlsanity.com/paper/2304.07014/) (2023)
- [LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering](https://mlsanity.com/paper/2111.14547/) (2021)
- [Permute Me Softly: Learning Soft Permutations for Graph Representations](https://mlsanity.com/paper/2110.01872/) (2021)
- [Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective](https://mlsanity.com/paper/2105.12918/) (2021)
- [Graph Representation Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2311.00291/) (2023)
- [Unified GCNs: Towards Connecting GCNs with CNNs](https://mlsanity.com/paper/2204.12300/) (2022)
- [GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection](https://mlsanity.com/paper/2401.09193/) (2024)
- [AKBR: Learning Adaptive Kernel-based Representations for Graph Classification](https://mlsanity.com/paper/2403.16130/) (2024)

## Abstract (arXiv)

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.