# A Data-Driven Approach to Dataflow-Aware Online Scheduling for Graph Neural Network Inference

arXiv: https://arxiv.org/abs/2411.16342 · HTML: https://mlsanity.com/paper/2411.16342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 10 of 10)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Computing Graph Neural Networks: A Survey from Algorithms to Accelerators](https://mlsanity.com/paper/2010.00130/) (2020)
- [HyGCN: A GCN Accelerator with Hybrid Architecture](https://mlsanity.com/paper/2001.02514/) (2020)
- [Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary](https://mlsanity.com/paper/2302.00985/) (2023)
- [Deep Reinforcement Learning based Online Scheduling Policy for Deep Neural Network Multi-Tenant Multi-Accelerator Systems](https://mlsanity.com/paper/2404.08950/) (2024)
- [QOPTLib: a Quantum Computing Oriented Benchmark for Combinatorial Optimization Problems](https://mlsanity.com/paper/2404.15852/) (2024)
- [Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation](https://mlsanity.com/paper/2205.13901/) (2022)
- [SALSA: Simulated Annealing based Loop-Ordering Scheduler for DNN Accelerators](https://mlsanity.com/paper/2304.12931/) (2023)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have shown significant promise in various domains, such as recommendation systems, bioinformatics, and network analysis. However, the irregularity of graph data poses unique challenges for efficient computation, leading to the development of specialized GNN accelerator architectures that surpass traditional CPU and GPU performance. Despite this, the structural diversity of input graphs results in varying performance across different GNN accelerators, depending on their dataflows. This variability in performance due to differing dataflows and graph properties remains largely unexplored, limiting the adaptability of GNN accelerators. To address this, we propose a data-driven framework for dataflow-aware latency prediction in GNN inference. Our approach involves training regressors to predict the latency of executing specific graphs on particular dataflows, using simulations on synthetic graphs. Experimental results indicate that our regressors can predict the optimal dataflow for a given graph with up to 91.28% accuracy and a Mean Absolute Percentage Error (MAPE) of 3.78%. Additionally, we introduce an online scheduling algorithm that uses these regressors to enhance scheduling decisions. Our experiments demonstrate that this algorithm achieves up to 3.17× speedup in mean completion time and 6.26× speedup in mean execution time compared to the best feasible baseline across all datasets.