# PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm

arXiv: https://arxiv.org/abs/2203.00638 · HTML: https://mlsanity.com/paper/2203.00638/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 70 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 30 of 51)

- [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)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [SIGN: Scalable Inception Graph Neural Networks](https://mlsanity.com/paper/2004.11198/) (2020)
- [Design Space for Graph Neural Networks](https://mlsanity.com/paper/2011.08843/) (2020)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [DeepInf: Social Influence Prediction with Deep Learning](https://mlsanity.com/paper/1807.05560/) (2018)
- [Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks](https://mlsanity.com/paper/1704.06803/) (2017)
- [Scalable Graph Neural Networks via Bidirectional Propagation](https://mlsanity.com/paper/2010.15421/) (2020)
- [Auto-GNN: Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/1909.03184/) (2019)
- [MotifNet: a motif-based Graph Convolutional Network for directed graphs](https://mlsanity.com/paper/1802.01572/) (2018)
- [Spam Review Detection with Graph Convolutional Networks](https://mlsanity.com/paper/1908.10679/) (2019)
- [GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs](https://mlsanity.com/paper/2006.06608/) (2020)

## Built on by (most cited first, 30 of 37)

- [Graph Attention Multi-Layer Perceptron](https://mlsanity.com/paper/2206.04355/) (2022)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [BlindFL: Vertical Federated Machine Learning without Peeking into Your Data](https://mlsanity.com/paper/2206.07975/) (2022)
- [Distributed Graph Neural Network Training: A Survey](https://mlsanity.com/paper/2211.00216/) (2022)
- [Graph Condensation for Inductive Node Representation Learning](https://mlsanity.com/paper/2307.15967/) (2023)
- [Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis](https://mlsanity.com/paper/2205.09702/) (2022)
- [Model Degradation Hinders Deep Graph Neural Networks](https://mlsanity.com/paper/2206.04361/) (2022)
- [NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search](https://mlsanity.com/paper/2206.09166/) (2022)
- [Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer](https://mlsanity.com/paper/2312.12467/) (2023)
- [Robust Mid-Pass Filtering Graph Convolutional Networks](https://mlsanity.com/paper/2302.08048/) (2023)
- [Rethinking Node-wise Propagation for Large-scale Graph Learning](https://mlsanity.com/paper/2402.06128/) (2024)
- [Search to Fine-tune Pre-trained Graph Neural Networks for Graph-level Tasks](https://mlsanity.com/paper/2308.06960/) (2023)
- [Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms](https://mlsanity.com/paper/2303.10875/) (2023)
- [NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning](https://mlsanity.com/paper/2206.08583/) (2022)
- [LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning](https://mlsanity.com/paper/2401.11772/) (2024)
- [OpenBox: A Python Toolkit for Generalized Black-box Optimization](https://mlsanity.com/paper/2304.13339/) (2023)
- [Graph Condensation for Open-World Graph Learning](https://mlsanity.com/paper/2405.17003/) (2024)
- [Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation](https://mlsanity.com/paper/2310.10998/) (2023)
- [RobGC: Towards Robust Graph Condensation](https://mlsanity.com/paper/2406.13200/) (2024)
- [Efficient Graph Neural Network Inference at Large Scale](https://mlsanity.com/paper/2211.00495/) (2022)
- [DivBO: Diversity-aware CASH for Ensemble Learning](https://mlsanity.com/paper/2302.03255/) (2023)
- [NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams](https://mlsanity.com/paper/2312.02473/) (2023)
- [Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning](https://mlsanity.com/paper/2411.17063/) (2024)
- [When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook](https://mlsanity.com/paper/2312.12477/) (2023)
- [Demystifying Higher-Order Graph Neural Networks](https://mlsanity.com/paper/2406.12841/) (2024)
- [LLM4GNAS: A Large Language Model Based Toolkit for Graph Neural Architecture Search](https://mlsanity.com/paper/2502.10459/) (2025)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach](https://mlsanity.com/paper/2501.11823/) (2025)
- [Adaptive Mesh-Quantization for Neural PDE Solvers](https://mlsanity.com/paper/2511.18474/) (2025)
- [Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks](https://mlsanity.com/paper/2304.11574/) (2023)

## Abstract (arXiv)

Graph neural networks (GNNs) have achieved state-of-the-art performance in various graph-based tasks. However, as mainstream GNNs are designed based on the neural message passing mechanism, they do not scale well to data size and message passing steps. Although there has been an emerging interest in the design of scalable GNNs, current researches focus on specific GNN design, rather than the general design space, limiting the discovery of potential scalable GNN models. This paper proposes PasCa, a new paradigm and system that offers a principled approach to systemically construct and explore the design space for scalable GNNs, rather than studying individual designs. Through deconstructing the message passing mechanism, PasCa presents a novel Scalable Graph Neural Architecture Paradigm (SGAP), together with a general architecture design space consisting of 150k different designs. Following the paradigm, we implement an auto-search engine that can automatically search well-performing and scalable GNN architectures to balance the trade-off between multiple criteria (e.g., accuracy and efficiency) via multi-objective optimization. Empirical studies on ten benchmark datasets demonstrate that the representative instances (i.e., PasCa-V1, V2, and V3) discovered by our system achieve consistent performance among competitive baselines. Concretely, PasCa-V3 outperforms the state-of-the-art GNN method JK-Net by 0.4% in terms of predictive accuracy on our large industry dataset while achieving up to 28.3× training speedups.