Publications | DAIR Lab

2023

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement

Xiaonan Nie, Xupeng Miao, Zilong Wang, and 5 more authors

Proceedings of the ACM on Management of Data, 2023

@article{nie2023flexmoe,
  title = {FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement},
  author = {Nie, Xiaonan and Miao, Xupeng and Wang, Zilong and Yang, Zichao and Xue, Jilong and Ma, Lingxiao and Cao, Gang and Cui, Bin},
  journal = {Proceedings of the ACM on Management of Data},
  volume = {1},
  number = {1},
  pages = {1--19},
  year = {2023}
}

Database

A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning

Xinyi Zhang, Zhuo Chang, Hong Wu, and 5 more authors

Proceedings of the ACM on Management of Data, 2023

Bib CCF-A Code

@article{zhang2023unified,
  title = {A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning},
  author = {Zhang, Xinyi and Chang, Zhuo and Wu, Hong and Li, Yang and Chen, Jia and Tan, Jian and Li, Feifei and Cui, Bin},
  journal = {Proceedings of the ACM on Management of Data},
  volume = {1},
  number = {2},
  pages = {1--26},
  year = {2023},
  publisher = {ACM New York, NY, USA}
}

Database

DBPA: A Benchmark for Transactional Database Performance Anomalies

Shiyue Huang, Ziwei Wang, Xinyi Zhang, and 3 more authors

Proceedings of the ACM on Management of Data, 2023

Bib CCF-A Code

@article{huang2023dbpa,
  title = {DBPA: A Benchmark for Transactional Database Performance Anomalies},
  author = {Huang, Shiyue and Wang, Ziwei and Zhang, Xinyi and Tu, Yaofeng and Li, Zhongliang and Cui, Bin},
  journal = {Proceedings of the ACM on Management of Data},
  volume = {1},
  number = {1},
  pages = {1--26},
  year = {2023},
  publisher = {ACM New York, NY, USA}
}

AutoML

VolcanoML: speeding up end-to-end AutoML via scalable search space decomposition

Yang Li, Yu Shen, Wentao Zhang, and 2 more authors

The VLDB Journal, 2023

Bib CCF-A Code

@article{li2023volcanoml,
  title = {VolcanoML: speeding up end-to-end AutoML via scalable search space decomposition},
  author = {Li, Yang and Shen, Yu and Zhang, Wentao and Zhang, Ce and Cui, Bin},
  journal = {The VLDB Journal},
  volume = {32},
  number = {2},
  pages = {389--413},
  year = {2023}
}

2022

ML system

Pasca: A graph neural architecture search system under the scalable paradigm

Wentao Zhang, Yu Shen, Zheyu Lin, and 6 more authors

In Proceedings of the ACM Web Conference 2022, 2022

Bib CCF-A Code

@inproceedings{zhang2022pasca,
  title = {Pasca: A graph neural architecture search system under the scalable paradigm},
  author = {Zhang, Wentao and Shen, Yu and Lin, Zheyu and Li, Yang and Li, Xiaosen and Ouyang, Wen and Tao, Yangyu and Yang, Zhi and Cui, Bin},
  booktitle = {Proceedings of the ACM Web Conference 2022},
  pages = {1817--1828},
  year = {2022}
}

Data-centric ML

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning

Wentao Zhang, Zeang Sheng, Mingyu Yang, and 4 more authors

In International Conference on Machine Learning, 2022

Bib CCF-A Code

@inproceedings{zhang2022nafs,
  title = {NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning},
  author = {Zhang, Wentao and Sheng, Zeang and Yang, Mingyu and Li, Yang and Shen, Yu and Yang, Zhi and Cui, Bin},
  booktitle = {International Conference on Machine Learning},
  pages = {26467--26483},
  year = {2022}
}

others

Diffusion models: A comprehensive survey of methods and applications

Ling Yang, Zhilong Zhang, Yang Song, and 6 more authors

ACM Computing Surveys, 2022

Bib

@article{yang2022diffusion,
  title = {Diffusion models: A comprehensive survey of methods and applications},
  author = {Yang, Ling and Zhang, Zhilong and Song, Yang and Hong, Shenda and Xu, Runsheng and Zhao, Yue and Zhang, Wentao and Cui, Bin and Yang, Ming-Hsuan},
  journal = {ACM Computing Surveys},
  year = {2022}
}

others

AutoDC: an automatic machine learning framework for disease classification

Yang Bai, Yang Li, Yu Shen, and 3 more authors

Bioinformatics, 2022

Bib Code

@article{bai2022autodc,
  title = {AutoDC: an automatic machine learning framework for disease classification},
  author = {Bai, Yang and Li, Yang and Shen, Yu and Yang, Mingyu and Zhang, Wentao and Cui, Bin},
  journal = {Bioinformatics},
  volume = {38},
  number = {13},
  pages = {3415--3421},
  year = {2022}
}

others

Graph neural networks in recommender systems: a survey

Shiwen Wu, Fei Sun, Wentao Zhang, and 2 more authors

ACM Computing Surveys, 2022

Bib

@article{wu2022graph,
  title = {Graph neural networks in recommender systems: a survey},
  author = {Wu, Shiwen and Sun, Fei and Zhang, Wentao and Xie, Xu and Cui, Bin},
  journal = {ACM Computing Surveys},
  volume = {55},
  number = {5},
  pages = {1--37},
  year = {2022}
}

others

Zoomer: Boosting retrieval on web-scale graphs by regions of interest

Yuezihan Jiang, Yu Cheng, Hanyu Zhao, and 6 more authors

In 2022 IEEE 38th International Conference on Data Engineering, 2022

Bib CCF-A Code

@inproceedings{jiang2022zoomer,
  title = {Zoomer: Boosting retrieval on web-scale graphs by regions of interest},
  author = {Jiang, Yuezihan and Cheng, Yu and Zhao, Hanyu and Zhang, Wentao and Miao, Xupeng and He, Yu and Wang, Liang and Yang, Zhi and Cui, Bin},
  booktitle = {2022 IEEE 38th International Conference on Data Engineering},
  pages = {2224--2236},
  year = {2022}
}

2021

Data-centric ML

Alg: Fast and accurate active learning framework for graph convolutional networks

Wentao Zhang, Yu Shen, Yang Li, and 3 more authors

In Proceedings of the 2021 International Conference on Management of Data, 2021

Bib CCF-A Code

@inproceedings{zhang2021alg,
  title = {Alg: Fast and accurate active learning framework for graph convolutional networks},
  author = {Zhang, Wentao and Shen, Yu and Li, Yang and Chen, Lei and Yang, Zhi and Cui, Bin},
  booktitle = {Proceedings of the 2021 International Conference on Management of Data},
  pages = {2366--2374},
  year = {2021}
}

Data-centric ML

GRAIN: improving data efficiency of graph neural networks via diversified influence maximization

Wentao Zhang, Zhi Yang, Yexin Wang, and 4 more authors

Proceedings of the VLDB Endowment, 2021

Bib CCF-A Code

@article{zhang2021grain,
  title = {GRAIN: improving data efficiency of graph neural networks via diversified influence maximization},
  author = {Zhang, Wentao and Yang, Zhi and Wang, Yexin and Shen, Yu and Li, Yang and Wang, Liang and Cui, Bin},
  journal = {Proceedings of the VLDB Endowment},
  volume = {14},
  number = {11},
  pages = {2473--2482},
  year = {2021},
  publisher = {VLDB Endowment}
}

Data-centric ML

Node dependent local smoothing for scalable graph learning

Wentao Zhang, Mingyu Yang, Zeang Sheng, and 5 more authors

Advances in Neural Information Processing Systems, 2021

Bib CCF-A Code

@article{zhang2021node,
  title = {Node dependent local smoothing for scalable graph learning},
  author = {Zhang, Wentao and Yang, Mingyu and Sheng, Zeang and Li, Yang and Ouyang, Wen and Tao, Yangyu and Yang, Zhi and Cui, Bin},
  journal = {Advances in Neural Information Processing Systems},
  volume = {34},
  pages = {20321--20332},
  year = {2021}
}

AutoML

Openbox: A generalized black-box optimization service

Yang Li, Yu Shen, Wentao Zhang, and 8 more authors

In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021

Bib CCF-A Code

@inproceedings{li2021openbox,
  title = {Openbox: A generalized black-box optimization service},
  author = {Li, Yang and Shen, Yu and Zhang, Wentao and Chen, Yuanwei and Jiang, Huaijun and Liu, Mingchao and Jiang, Jiawei and Gao, Jinyang and Wu, Wentao and Yang, Zhi and others},
  booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},
  pages = {3209--3219},
  year = {2021}
}