Summary of Adaptive Soft Error Protection For Neural Network Processing, by Xinghua Xue et al.
Adaptive Soft Error Protection for Neural Network Processing
by Xinghua Xue, Cheng Liu, Feng Min, Yinhe Han
First submitted to arxiv on: 29 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to mitigate soft errors in neural networks (NNs) by capturing input- and component-specific vulnerability to soft errors using a lightweight graph neural network (GNN) model. The proposed model facilitates runtime vulnerability prediction, enabling an adaptive protection strategy that dynamically adjusts to varying vulnerabilities. This approach complements classical fault-tolerant techniques by tailoring protection efforts based on real-time vulnerability assessments. Experimental results demonstrate that the adaptive protection method achieves a 42.12% average reduction in computational overhead compared to prior static vulnerability-based approaches, without compromising reliability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper finds a new way to make neural networks more reliable when they’re affected by soft errors. Soft errors happen when there’s an unexpected problem with the data going into or being processed by the network. Right now, people usually try to fix this by making sure certain parts of the network are extra safe. But this approach doesn’t work well if the problem is changing as the network is working. The new method uses a special kind of neural network that can figure out what’s likely to go wrong and adjust its protection based on that. This helps make the network more reliable without wasting time or resources. |
Keywords
» Artificial intelligence » Gnn » Graph neural network » Neural network
