# Phases, Modalities, Temporal and Spatial Locality: Domain Specific ML Prefetcher for Accelerating Graph Analytics

arXiv: https://arxiv.org/abs/2212.05250 · HTML: https://mlsanity.com/paper/2212.05250/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 94 references that are in the map.
- First posted on arXiv 10 Dec 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data](https://mlsanity.com/paper/1612.08544/) (2016)
- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [Incorporating Domain Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2103.00180/) (2021)
- [Reactive Soft Prototype Computing for Concept Drift Streams](https://mlsanity.com/paper/2007.05432/) (2020)
- [Learning Memory Access Patterns](https://mlsanity.com/paper/1803.02329/) (2018)
- [SISA: Set-Centric Instruction Set Architecture for Graph Mining on Processing-in-Memory Systems](https://mlsanity.com/paper/2104.07582/) (2021)
- [GraphLab: A New Framework For Parallel Machine Learning](https://mlsanity.com/paper/1408.2041/) (2014)
- [An Empirical Guide to the Behavior and Use of Scalable Persistent Memory](https://mlsanity.com/paper/1908.03583/) (2019)
- [Fine-Grained Address Segmentation for Attention-Based Variable-Degree Prefetching](https://mlsanity.com/paper/2205.02269/) (2022)
- [GraphMat: High performance graph analytics made productive](https://mlsanity.com/paper/1503.07241/) (2015)
- [Accelerating PageRank using Partition-Centric Processing](https://mlsanity.com/paper/1709.07122/) (2017)

## Built on by (most cited first, 1 of 1)

- [Attention, Distillation, and Tabularization: Towards Practical Neural Network-Based Prefetching](https://mlsanity.com/paper/2401.06362/) (2023)

## Abstract (arXiv)

Memory performance is a bottleneck in graph analytics acceleration. Existing Machine Learning (ML) prefetchers struggle with phase transitions and irregular memory accesses in graph processing. We propose MPGraph, an ML-based Prefetcher for Graph analytics using domain specific models. MPGraph introduces three novel optimizations: soft detection for phase transitions, phase-specific multi-modality models for access delta and page predictions, and chain spatio-temporal prefetching (CSTP) for prefetch control. Our transition detector achieves 34.17-82.15% higher precision compared with Kolmogorov-Smirnov Windowing and decision tree. Our predictors achieve 6.80-16.02% higher F1-score for delta and 11.68-15.41% higher accuracy-at-10 for page prediction compared with LSTM and vanilla attention models. Using CSTP, MPGraph achieves 12.52-21.23% IPC improvement, outperforming state-of-the-art non-ML prefetcher BO by 7.58-12.03% and ML-based prefetchers Voyager and TransFetch by 3.27-4.58%. For practical implementation, we demonstrate MPGraph using compressed models with reduced latency shows significantly superior accuracy and coverage compared with BO, leading to 3.58% higher IPC improvement.