Search Results for author: Jianxun Liu

Found 7 papers, 2 papers with code

Evolutionary Architecture Search for Graph Neural Networks

no code implementations21 Sep 2020 Min Shi, David A. Wilson, Xingquan Zhu, Yu Huang, Yuan Zhuang, Jianxun Liu, Yufei Tang

In particular, Neural Architecture Search (NAS) has seen significant attention throughout the AutoML research community, and has pushed forward the state-of-the-art in a number of neural models to address grid-like data such as texts and images.

Neural Architecture Search Representation Learning

Multi-Label Graph Convolutional Network Representation Learning

no code implementations26 Dec 2019 Min Shi, Yufei Tang, Xingquan Zhu, Jianxun Liu

The multi-label network nodes not only have multiple labels for each node, such labels are often highly correlated making existing methods ineffective or fail to handle such correlation for node representation learning.

Multi-Label Classification Node Classification +1

Feature-Attention Graph Convolutional Networks for Noise Resilient Learning

no code implementations26 Dec 2019 Min Shi, Yufei Tang, Xingquan Zhu, Jianxun Liu

By using spectral-based graph convolution aggregation process, each node is allowed to concentrate more on the most determining neighborhood features aligned with the corresponding learning task.

Feature Importance

ClassyTune: A Performance Auto-Tuner for Systems in the Cloud

no code implementations12 Oct 2019 Yuqing Zhu, Jianxun Liu

Performance tuning can improve the system performance and thus enable the reduction of cloud computing resources needed to support an application.

BestConfig: Tapping the Performance Potential of Systems via Automatic Configuration Tuning

1 code implementation10 Oct 2017 Yuqing Zhu, Jianxun Liu, Mengying Guo, Yungang Bao, Wenlong Ma, Zhuoyue Liu, Kunpeng Song, Yingchun Yang

To help users tap the performance potential of systems, we present BestConfig, a system for automatically finding a best configuration setting within a resource limit for a deployed system under a given application workload.

Performance Databases Distributed, Parallel, and Cluster Computing Software Engineering

ACTS in Need: Automatic Configuration Tuning with Scalability Guarantees

1 code implementation4 Aug 2017 Yuqing Zhu, Jianxun Liu, Mengying Guo, Wenlong Ma, Yungang Bao

To support the variety of Big Data use cases, many Big Data related systems expose a large number of user-specifiable configuration parameters.

Distributed, Parallel, and Cluster Computing

Cannot find the paper you are looking for? You can Submit a new open access paper.