# Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification

arXiv: https://arxiv.org/abs/2406.16357 · HTML: https://mlsanity.com/paper/2406.16357/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 59 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 30 of 30)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Graph Neural Networks with convolutional ARMA filters](https://mlsanity.com/paper/1901.01343/) (2019)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [Implicit Graph Neural Networks](https://mlsanity.com/paper/2009.06211/) (2020)
- [Computing Graph Neural Networks: A Survey from Algorithms to Accelerators](https://mlsanity.com/paper/2010.00130/) (2020)
- [A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models](https://mlsanity.com/paper/1908.01297/) (2019)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [GraphNAS: Graph Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1904.09981/) (2019)
- [Automated Machine Learning on Graphs: A Survey](https://mlsanity.com/paper/2103.00742/) (2021)
- [Robust Graph Learning from Noisy Data](https://mlsanity.com/paper/1812.06673/) (2018)
- [Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets](https://mlsanity.com/paper/2103.00794/) (2021)
- [Rethinking Graph Neural Architecture Search from Message-passing](https://mlsanity.com/paper/2103.14282/) (2021)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Spectral Graph Attention Network with Fast Eigen-approximation](https://mlsanity.com/paper/2003.07450/) (2020)
- [Power up! Robust Graph Convolutional Network via Graph Powering](https://mlsanity.com/paper/1905.10029/) (2019)
- [AutoGL: A Library for Automated Graph Learning](https://mlsanity.com/paper/2104.04987/) (2021)
- [Semi-Supervised Hierarchical Graph Classification](https://mlsanity.com/paper/2206.05416/) (2022)
- [Knowledge Graph Completion with Counterfactual Augmentation](https://mlsanity.com/paper/2302.13083/) (2023)
- [Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/2208.06651/) (2022)
- [HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking](https://mlsanity.com/paper/1909.00122/) (2019)

## Built on by (most cited first, 2 of 2)

- [Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling](https://mlsanity.com/paper/2502.16239/) (2025)
- [Exploring Spatial-Temporal Representation via Star Graph for mmWave Radar-based Human Activity Recognition](https://mlsanity.com/paper/2512.12013/) (2025)

## Abstract (arXiv)

Graph Neural Architecture Search (GNAS) has achieved superior performance on various graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS in resource-constraint scenarios. This paper proposes to design a joint graph data and architecture mechanism, which identifies important sub-architectures via the valuable graph data. To search for optimal lightweight Graph Neural Networks (GNNs), we propose a Lightweight Graph Neural Architecture Search with Graph SparsIfication and Network Pruning (GASSIP) method. In particular, GASSIP comprises an operation-pruned architecture search module to enable efficient lightweight GNN search. Meanwhile, we design a novel curriculum graph data sparsification module with an architecture-aware edge-removing difficulty measurement to help select optimal sub-architectures. With the aid of two differentiable masks, we iteratively optimize these two modules to efficiently search for the optimal lightweight architecture. Extensive experiments on five benchmarks demonstrate the effectiveness of GASSIP. Particularly, our method achieves on-par or even higher node classification performance with half or fewer model parameters of searched GNNs and a sparser graph.