# LookHops: light multi-order convolution and pooling for graph classification

arXiv: https://arxiv.org/abs/2012.15741 · HTML: https://mlsanity.com/paper/2012.15741/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2204.07321/) (2022)
- [PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding](https://mlsanity.com/paper/2302.07120/) (2023)
- [On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling](https://mlsanity.com/paper/2306.12726/) (2023)
- [Pose-based Tremor Classification for Parkinson's Disease Diagnosis from Video](https://mlsanity.com/paper/2207.06828/) (2022)

## Abstract (arXiv)

Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive k-order(k>1) method requires more computation cost, limiting the further applications. In this paper, we investigate the strategy of selecting k via neighborhood information gain and propose light k-order convolution and pooling requiring fewer parameters while improving the performance. Comprehensive and fair experiments through six graph classification benchmarks show: 1) the performance improvement is consistent to the k-order information gain. 2) the proposed convolution requires fewer parameters while providing competitive results. 3) the proposed pooling outperforms SOTA algorithms in terms of efficiency and performance.