Factorized Deep Retrieval and Distributed TensorFlow Serving

By Xinyang Yi, Yi-Fan Chen, Sukriti Ramesh, Vinu Rajashekhar, Lichan Hong, Noah Fiedel, Nandini Seshadri, Lukasz Heldt, Xiang Wu, Ed H. Chi. 2018

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Sustainable AI: Environmental Implications, Challenges and Opportunities (2021, background): “Similarly, Figure 2(c) illustrates that between 2019 and 2021, the size of recommendation models at Facebook has increased by 20 × [15], [16], [17], [11].”
TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models (2021, background): “Furthermore, the memory capacity requirement for state-of-the-art recommendation models has grown into the scale of terabytes (Lui et al., 2021; Yi et al., 2018; Zhao et al., 2019; 2020).”
Understanding Training Efficiency of Deep Learning Recommendation Models at Scale (2020, background): “The memory capacity of embedding tables have increased dramatically from tens of GBs to TBs throughout the industry [36], [56], [58]–[60].”
Understanding Capacity-Driven Scale-Out Neural Recommendation Inference (2020, methodology): “Figure 1 shows the rate of recommendation model growth at Facebook, and further models at the 110TB scale have been cited by Baidu and Google [10]– [12].”