101 citations · 127 across the 9 of their papers we have counts for
9 papers
Teacher-Student Architecture for Knowledge Distillation: A Survey
Chengming Hu, Xuan Li, Dan Liu +4
Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their…
Detecting and Grounding Important Characters in Visual Stories
Danyang Liu, Frank Keller
Characters are essential to the plot of any story. Establishing the characters before writing a story can improve the clarity of the plot and the overall flow of the narrative. How…
Ternary Quantization: A Survey
Dan Liu, Xue Liu
Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to compress neural network models with fast…
Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuning
Dan Liu, Xue Liu
Most existing pruning works are resource-intensive, requiring retraining or fine-tuning of the pruned models for accuracy. We propose a retraining-free pruning method based on hype…
Pruning Ternary Quantization
Dan Liu, Xi Chen, Jie Fu +2
Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult…
Multi-objective Evolutionary Algorithms are Generally Good: Maximizing Monotone Submodular Functions over Sequences
Chao Qian, Dan-Xuan Liu, Chao Feng +1
Evolutionary algorithms (EAs) are general-purpose optimization algorithms, inspired by natural evolution. Recent theoretical studies have shown that EAs can achieve good approximat…
Solvability of a Regular Polynomial Vector Optimization Problem without Convexity
Danyang Liu, Rong Hu, Yaping Fang
In this paper we consider the solvability of a non-convex regular polynomial vector optimization problem on a nonempty closed set. We introduce regularity conditions for the polyno…
KRED: Knowledge-Aware Document Representation for News Recommendations
Danyang Liu, Jianxun Lian, Shiyin Wang +4
News articles usually contain knowledge entities such as celebrities or organizations. Important entities in articles carry key messages and help to understand the content in a mor…
Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems
Xiao Zhou, Danyang Liu, Jianxun Lian +1
The success of recommender systems in modern online platforms is inseparable from the accurate capture of users' personal tastes. In everyday life, large amounts of user feedback d…