118 citations · 184 across the 7 of their papers we have counts for
7 papers
MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning
Shiming Chen, Ziming Hong, Guo-Sen Xie +5
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable kn…
Modular Tree Network for Source Code Representation Learning
Wenhan Wang, Ge Li, Sijie Shen +2
Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing…
Learning to Represent Programs with Heterogeneous Graphs
Kechi Zhang, Wenhan Wang, Huangzhao Zhang +2
Program source code contains complex structure information, which can be represented in structured data forms like trees or graphs. To acquire the structural information in source…
Towards Full-line Code Completion with Neural Language Models
Wenhan Wang, Sijie Shen, Ge Li +1
A code completion system suggests future code elements to developers given a partially-complete code snippet. Code completion is one of the most useful features in Integrated Devel…
Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
Wenhan Wang, Ge Li, Bo Ma +2
Code clones are semantically similar code fragments pairs that are syntactically similar or different. Detection of code clones can help to reduce the cost of software maintenance…
Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models
Minjia Zhang, Xiaodong Liu, Wenhan Wang +2
Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs a…
Learning Intrinsic Sparse Structures within Long Short-Term Memory
Wei Wen, Yuxiong He, Samyam Rajbhandari +6
Model compression is significant for the wide adoption of Recurrent Neural Networks (RNNs) in both user devices possessing limited resources and business clusters requiring quick r…