English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Deep learning has brought great progress for the sequential recommendation(SR) tasks. With advanced network architectures, sequential recommender modelscan be stacked with many hidden layers, e.g., up to 100 layers on real-worldrecommendation datasets. Training such a deep network is difficult because itcan be computationally very expensive and takes much longer time, especially insituations where there are tens of billions of user-item interactions. To dealwith such a challenge, we present StackRec, a simple, yet very effective andefficient training framework for deep SR models by iterative layer stacking.Specifically, we first offer an important insight that hidden layers/blocks ina well-trained deep SR model have very similar distributions. Enlightened bythis, we propose the stacking operation on the pre-trained layers/blocks totransfer knowledge from a shallower model to a deep model, then we performiterative stacking so as to yield a much deeper but easier-to-train SR model.We validate the performance of StackRec by instantiating it with fourstate-of-the-art SR models in three practical scenarios with real-worlddatasets. Extensive experiments show that StackRec achieves not only comparableperformance, but also substantial acceleration in training time, compared to SRmodels that are trained from scratch. Codes are available athttps://github.com/wangjiachun0426/StackRec.

StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking