132 citations · 164 across the 11 of their papers we have counts for
8 papers · 1 filter
Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models
Daochen Zha, Louis Feng, Liang Luo +8
Sharding a large machine learning model across multiple devices to balance the costs is important in distributed training. This is challenging because partitioning is NP-hard, and…
DreamShard: Generalizable Embedding Table Placement for Recommender Systems
Daochen Zha, Louis Feng, Qiaoyu Tan +6
We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e.g., GPUs) to balance the comput…
Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems
Mao Ye, Ruichen Jiang, Haoxiang Wang +6
One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and…
AutoShard: Automated Embedding Table Sharding for Recommender Systems
Daochen Zha, Louis Feng, Bhargav Bhushanam +7
Embedding learning is an important technique in deep recommendation models to map categorical features to dense vectors. However, the embedding tables often demand an extremely lar…
Building a Performance Model for Deep Learning Recommendation Model Training on GPUs
Zhongyi Lin, Louis Feng, Ehsan K. Ardestani +5
We devise a performance model for GPU training of Deep Learning Recommendation Models (DLRM), whose GPU utilization is low compared to other well-optimized CV and NLP models. We sh…
Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data
Mao Ye, Dhruv Choudhary, Jiecao Yu +6
Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at gr…
Training Recommender Systems at Scale: Communication-Efficient Model and Data Parallelism
Vipul Gupta, Dhruv Choudhary, Ping Tak Peter Tang +6
In this paper, we consider hybrid parallelism -- a paradigm that employs both Data Parallelism (DP) and Model Parallelism (MP) -- to scale distributed training of large recommendat…
Automatic Anomaly Detection in the Cloud Via Statistical Learning
Jordan Hochenbaum, Owen S. Vallis, Arun Kejariwal
Performance and high availability have become increasingly important drivers, amongst other drivers, for user retention in the context of web services such as social networks, and…