• Computer Science
  • Published in ArXiv 2019

The Architectural Implications of Facebook's DNN-based Personalized Recommendation

@article{Gupta2019TheAI,
  title={The Architectural Implications of Facebook's DNN-based Personalized Recommendation},
  author={Udit Gupta and Xiaodong Wang and Maxim Naumov and Carole-Jean Wu and Brandon Reagen and David Brooks and Bradford Cottel and Kim Hazelwood and Bill Jia and Hsien-Hsin S. Lee and Andrey Malevich and Dheevatsa Mudigere and Mikhail Smelyanskiy and Liang Xiong and Xuan Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.03109}
}
The widespread application of deep learning has changed the landscape of computation in the data center. In particular, personalized recommendation for content ranking is now largely accomplished leveraging deep neural networks. However, despite the importance of these models and the amount of compute cycles they consume, relatively little research attention has been devoted to systems for recommendation. To facilitate research and to advance the understanding of these workloads, this paper… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

VIEW 19 EXCERPTS
CITES BACKGROUND & METHODS

A Disaggregated Memory System for Deep Learning

VIEW 1 EXCERPT
CITES BACKGROUND

Exploiting Parallelism Opportunities with Deep Learning Frameworks

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 50 REFERENCES

Applied Machine Learning at Facebook: A Datacenter Infrastructure Perspective

VIEW 4 EXCERPTS

Neural Collaborative Filtering

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

You Only Look Once: Unified, Real-Time Object Detection

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Exploring neural transducers for end-to-end speech recognition

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

In-datacenter performance analysis of a tensor processing unit

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Deep Neural Networks for YouTube Recommendations

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Wide & Deep Learning for Recommender Systems

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL