An open framework shows sliding-window training on long sequences is practical for recommenders, with a k-shift embedding enabling million-scale vocabularies on commodity GPUs and up to 6% gains on Retailrocket at 4x training cost.
Judicial support tool: Finding the k most likely judicial worlds
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Reinforcement learning policies for time-constrained slate recommendations improve engagement over contextual bandits in e-commerce settings.
citing papers explorer
-
Is Sliding Window All You Need? An Open Framework for Long-Sequence Recommendation
An open framework shows sliding-window training on long sequences is practical for recommenders, with a k-shift embedding enabling million-scale vocabularies on commodity GPUs and up to 6% gains on Retailrocket at 4x training cost.
-
Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce
Reinforcement learning policies for time-constrained slate recommendations improve engagement over contextual bandits in e-commerce settings.