# Motif-based Convolutional Neural Network on Graphs

arXiv: https://arxiv.org/abs/1711.05697 · HTML: https://mlsanity.com/paper/1711.05697/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

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

- [Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing](https://mlsanity.com/paper/2102.08786/) (2021)
- [Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs](https://mlsanity.com/paper/2210.13710/) (2022)
- [Motif Graph Neural Network](https://mlsanity.com/paper/2112.14900/) (2021)
- [Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification](https://mlsanity.com/paper/2412.09044/) (2024)
- [Sparsity-aware neural user behavior modeling in online interaction platforms](https://mlsanity.com/paper/2202.13491/) (2022)
- [Capturing Fine-grained Semantics in Contrastive Graph Representation Learning](https://mlsanity.com/paper/2304.11658/) (2023)
- [Protein-Based Fish Species Identification: Dataset, Models, and Insights from Native Bangladeshi Fish](https://mlsanity.com/paper/2606.18302/) (2026)

## Abstract (arXiv)

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supervised node classification on real-world social networks and multiple representative heterogeneous graph datasets indicate significant gains of 6-21% over existing graph CNNs and other state-of-the-art techniques.