5 citations · 11 across the 5 of their papers we have counts for
3 papers · 1 filter
GACT: Activation Compressed Training for Generic Network Architectures
Xiaoxuan Liu, Lianmin Zheng, Dequan Wang +9
Training large neural network (NN) models requires extensive memory resources, and Activation Compressed Training (ACT) is a promising approach to reduce training memory footprint.…
Leveraging Application Data Constraints to Optimize Database-Backed Web Applications
Xiaoxuan Liu, Shuxian Wang, Mengzhu Sun +7
Exploiting the relationships among data is a classical query optimization technique. As persistent data is increasingly being created and maintained programmatically, prior work th…
Long-run User Value Optimization in Recommender Systems through Content Creation Modeling
Akos Lada, Xiaoxuan Liu, Jens Rischbieth +2
Content recommender systems are generally adept at maximizing immediate user satisfaction but to optimize for the \textit{long-run} user value, we need more statistically sophistic…