39 citations · 84 across the 12 of their papers we have counts for
12 papers
Learning to Branch in Combinatorial Optimization with Graph Pointer Networks
Rui Wang, Zhiming Zhou, Tao Zhang +4
Branch-and-bound is a typical way to solve combinatorial optimization problems. This paper proposes a graph pointer network model for learning the variable selection policy in the…
Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning
Mingyang Geng, Shangwen Wang, Dezun Dong +5
Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a…
Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding
Deze Wang, Zhouyang Jia, Shanshan Li +4
With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to co…
CD-SGD: Distributed Stochastic Gradient Descent with Compression and Delay Compensation
Enda Yu, Dezun Dong, Yemao Xu +2
Communication overhead is the key challenge for distributed training. Gradient compression is a widely used approach to reduce communication traffic. When combining with parallel c…
ConfInLog: Leveraging Software Logs to Infer Configuration Constraints
Shulin Zhou, Xiaodong Liu, Shanshan Li +5
Misconfigurations have become the dominant causes of software failures in recent years, drawing tremendous attention for their increasing prevalence and severity. Configuration con…
deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search
Chen Zeng, Yue Yu, Shanshan Li +6
With the rapid increase in the amount of public code repositories, developers maintain a great desire to retrieve precise code snippets by using natural language. Despite existing…
DepOwl: Detecting Dependency Bugs to Prevent Compatibility Failures
Zhouyang Jia, Shanshan Li, Tingting Yu +5
Applications depend on libraries to avoid reinventing the wheel. Libraries may have incompatible changes during evolving. As a result, applications will suffer from compatibility f…
A parallel structured divide-and-conquer algorithm for symmetric tridiagonal eigenvalue problems
Xia Liao, Shengguo Li, Yutong Lu +1
In this paper, a parallel structured divide-and-conquer (PSDC) eigensolver is proposed for symmetric tridiagonal matrices based on ScaLAPACK and a parallel structured matrix multip…
OD-SGD: One-step Delay Stochastic Gradient Descent for Distributed Training
Yemao Xu, Dezun Dong, Weixia Xu +1
The training of modern deep learning neural network calls for large amounts of computation, which is often provided by GPUs or other specific accelerators. To scale out to achieve…
Differential Neutrino Condensation onto Cosmic Structure
Hao-Ran Yu, J. D. Emberson, Derek Inman +12
Astrophysical techniques have pioneered the discovery of neutrino mass properties. Current cosmological observations give an upper bound on neutrino masses by attempting to disenta…
New fast divide-and-conquer algorithms for the symmetric tridiagonal eigenvalue problem
Shengguo Li, Xiangke Liao, Jie Liu +1
In this paper, two accelerated divide-and-conquer algorithms are proposed for the symmetric tridiagonal eigenvalue problem, which cost {flops} in the worst case, where $N…
On the Shoulders of Giants: Incremental Influence Maximization in Evolving Social Networks
Xiaodong Liu, Xiangke Liao, Shanshan Li +4
Identifying the most influential individuals can provide invaluable help in developing and deploying effective viral marketing strategies. Previous studies mainly focus on designin…