Summary of Novel Representation Learning Technique Using Graphs For Performance Analytics, by Tarek Ramadan et al.
Novel Representation Learning Technique using Graphs for Performance Analytics
by Tarek Ramadan, Ankur Lahiry, Tanzima Z. Islam
First submitted to arxiv on: 19 Jan 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 The proposed approach transforms tabular performance data into graphs, leveraging Graph Neural Networks (GNNs) to capture complex relationships between features and samples. This addresses two gaps: leveraging sample relationships directly and improving the fidelity of predictive models through high-quality embeddings. The method builds a graph by inferring edges based on feature similarities between samples. Evaluation demonstrates that even with 25% random missing values, GNN-based embeddings outperform state-of-the-art approaches for regression tasks in HPC and Machine Learning datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers developed a new way to work with data from High Performance Computing (HPC). They took tabular data and turned it into graphs. This is special because most computer systems already know how to work with graph data. The scientists used this graph data to train machines to make predictions about things like execution time. Their approach was better than other methods, even when some of the data was missing. This can help us make more accurate predictions and improve our understanding of complex systems. |
Keywords
* Artificial intelligence * Gnn * Machine learning * Regression
