Paper Info
Title
StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
Abstract
ABSTRACTDeep learning has brought great progress for the sequential recommendation (SR) tasks. With advanced network architectures, sequential recommender models can be stacked with many hidden layers, e.g., up to 100 layers on real-world recommendation datasets. Training such a deep network is difficult because it can be computationally very expensive and takes much longer time, especially in situations where there are tens of billions of user-item interactions. To deal with such a challenge, we present StackRec, a simple, yet very effective and efficient training framework for deep SR models by iterative layer stacking. Specifically, we first offer an important insight that hidden layers/blocks in a well-trained deep SR model have very similar distributions. Enlightened by this, we propose the stacking operation on the pre-trained layers/blocks to transfer knowledge from a shallower model to a deep model, then we perform iterative stacking so as to yield a much deeper but easier-to-train SR model. We validate the performance of StackRec by instantiating it with four state-of-the-art SR models in three practical scenarios with real-world datasets. Extensive experiments show that StackRec achieves not only comparable performance, but also substantial acceleration in training time, compared to SR models that are trained from scratch. Codes are available at https://github.com/wangjiachun0426/StackRec.
Year
DOI
Venue
2021
10.1145/3404835.3462890
Research and Development in Information Retrieval
Keywords
DocType
Citations 
Recommender systems, Knowledge Transfer, Training acceleration
Conference
1
PageRank 
References 
Authors
0.37
0
7
Name
Order
Citations
PageRank
Jiachun Wang110.70
Fajie Yuan214314.55
Jian Chen3324.31
Wu Qingyao425933.46
Min Yang57720.41
Yang Sun630.85
Guoxiao Zhang720.73