# GCN-ABFT: Low-Cost Online Error Checking for Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2412.18534 · HTML: https://mlsanity.com/paper/2412.18534/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [Computing Graph Neural Networks: A Survey from Algorithms to Accelerators](https://mlsanity.com/paper/2010.00130/) (2020)
- [Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis](https://mlsanity.com/paper/2205.09702/) (2022)
- [Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs](https://mlsanity.com/paper/2104.09455/) (2021)
- [GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks](https://mlsanity.com/paper/2203.00158/) (2022)
- [SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators](https://mlsanity.com/paper/2301.10388/) (2023)
- [Error Checking for Sparse Systolic Tensor Arrays](https://mlsanity.com/paper/2402.10850/) (2024)

## Built on by (most cited first, 3 of 3)

- [Custom Algorithm-based Fault Tolerance for Attention Layers in Transformers](https://mlsanity.com/paper/2507.16676/) (2025)
- [Periodic Online Testing for Sparse Systolic Tensor Arrays](https://mlsanity.com/paper/2504.18628/) (2025)
- [Syndrome Decoding for Silent Data Corruption in Quantized Integer GPU Arithmetic](https://mlsanity.com/paper/2609.19743/) (2026)

## Abstract (arXiv)

Graph convolutional networks (GCNs) are popular for building machine-learning application for graph-structured data. This widespread adoption led to the development of specialized GCN hardware accelerators. In this work, we address a key architectural challenge for GCN accelerators: how to detect errors in GCN computations arising from random hardware faults with the least computation cost. Each GCN layer performs a graph convolution, mathematically equivalent to multiplying three matrices, computed through two separate matrix multiplications. Existing Algorithm-based Fault Tolerance(ABFT) techniques can check the results of individual matrix multiplications. However, for a GCN layer, this check should be performed twice. To avoid this overhead, this work introduces GCN-ABFT that directly calculates a checksum for the entire three-matrix product within a single GCN layer, providing a cost-effective approach for error detection in GCN accelerators. Experimental results demonstrate that GCN-ABFT reduces the number of operations needed for checksum computation by over 21% on average for representative GCN applications. These savings are achieved without sacrificing fault-detection accuracy, as evidenced by the presented fault-injection analysis.