Sibei Chen

Sibei Chen

Auto-generated profile, based on publicly available information

Sibei Chen

Renmin University of China, Beijing, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 May 2023 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
SCSibei Chen
Sibei Chen
NTNan Tang
Nan Tang
JFJu Fan
Ju Fan
XYXuemi Yan
Xuemi Yan
CCChengliang Chai
Chengliang Chai
XDXiaoyong Du
Xiaoyong Du
Data preparation is crucial in achieving optimized results for machine learning (ML). However, having a good data preparation pipeline is highly non-trivial for ML practitioners, which is not only domain-specific, but also dataset-specific. There are two common practices. Human-generated pipelines (HI-pipelines) typically use a wide range of any operations or libraries but are highly experience- and heuristic-based. In contrast, machine-generated pipelines (AI-pipelines), a.k.a. AutoML, often adopt a predefined set of sophisticated operations and are search-based and optimized. These two common practices are mutually complementary. In this paper, we study a new problem that, given an HI-pipeline and an AI-pipeline for the same ML task, can we combine them to get a new pipeline (HAI-pipeline) that is better than the provided HI-pipeline and AI-pipeline? We propose HAIPipe, a framework to address the problem, which adopts an enumeration-sampling strategy to carefully select the best performing combined pipeline. We also introduce a reinforcement learning (RL) based approach to search an optimized AI-pipeline. Extensive experiments using 1400+ real-world HI-pipelines (Jupyter notebooks from Kaggle) verify that HAIPipe can significantly outperform the approaches using either HI-pipelines or AI-pipelines alone.

10 February 2025 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
SCSibei Chen
Sibei Chen
JFJu Fan
Ju Fan
BWBin Wu
Bin Wu
NTNan Tang
Nan Tang
CDChao Deng
Chao Deng
XDXiaoyong Du
Xiaoyong Du
Database management system (DBMS) configuration debugging, e.g., diagnosing poorly configured DBMS knobs and generating troubleshooting recommendations, is crucial in optimizing DBMS performance. However, the configuration debugging process is tedious and, sometimes challenging, even for seasoned database administrators (DBAs) with sufficient experience in DBMS configurations and good understandings of the DBMS internals (e.g., MySQL or Oracle). To address this difficulty, we propose Andromeda, a framework that utilizes large language models (LLMs) to enable automatic DBMS configuration debugging. Andromeda serves as a natural surrogate of DBAs to answer a wide range of natural language (NL) questions on DBMS configuration issues, and to generate diagnostic suggestions to fix these issues. Nevertheless, directly prompting LLMs with these professional questions may result in overly generic and often unsatisfying answers. To this end, we propose a retrieval-augmented generation (RAG) strategy that effectively provides matched domain-specific contexts for the question from multiple sources. They come from related historical questions, troubleshooting manuals and DBMS telemetries, which significantly improve the performance of configuration debugging. To support the RAG strategy, we develop a document retrieval mechanism addressing heterogeneous documents and design an effective method for telemetry analysis. Extensive experiments on real-world DBMS configuration debugging datasets show that Andromeda significantly outperforms existing solutions.

29 May 2024 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
SCSibei Chen
Sibei Chen
YHYeye He
Yeye He
WCWeiwei Cui
Weiwei Cui
JFJu Fan
Ju Fan
SGSong Ge
Song Ge
SCSurajit Chaudhuri
Surajit Chaudhuri
Spreadsheets are widely recognized as the most popular end-user programming tools, which blend the power of formula-based computation, with an intuitive table-based interface. Today, spreadsheets are used by billions of users to manipulate tables, most of whom are neither database experts nor professional programmers. Despite the success of spreadsheets, authoring complex formulas remains challenging, as non-technical users need to look up and understand non-trivial formula syntax. To address this pain point, we leverage the observation that there is often an abundance of similar-looking spreadsheets in the same organization, which not only have similar data, but also share similar computation logic encoded as formulas. We develop an Auto-Formula system that can accurately predict formulas that users want to author in a target spreadsheet cell, by learning and adapting formulas that already exist in similar spreadsheets, using contrastive-learning techniques inspired by "similar-face recognition" from compute vision. Extensive evaluations on over 2K test formulas extracted from real enterprise spreadsheets show the effectiveness of Auto-Formula over alternatives. Our benchmark data is available at https://github.com/microsoft/Auto-Formula to facilitate future research.

9 June 2024
Verified
Conference Paper
Open access
SCSibei Chen
Sibei Chen
HLHanbing Liu
Hanbing Liu
WJWaiting Jin
Waiting Jin
XSXiangyu Sun
Xiangyu Sun
XFXiaoyao Feng
Xiaoyao Feng
NTNan Tang
Nan Tang
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive capabilities of large language models like ChatGPT in generating programs by inter- acting with users through natural language prompts, there are still limitations. Specifically, a user must provide specific prompts to iteratively guide ChatGPT in improving data preparation programs, which requires a certain level of expertise in programming, the dataset used and the ML task. Moreover, once a program has been generated, it is non-trivial to revisit a previous version or make changes to the program without starting the process over again. In this paper, we present ChatPipe, a novel system designed to facilitate seamless interaction between users and ChatGPT. Chat- Pipe provides users with effective recommendation on next data preparation operations, and guides ChatGPT to generate program for the operations. Also, ChatPipe enables users to easily roll back to previous versions of the program, which facilitates more efficient experimentation and testing. We have developed a web application for ChatPipe and prepared several real-world ML tasks from Kaggle, which can demonstrate the capabilities of ChatPipe.


1 January 2016
Verified
Journal Article
Closed access
LSLing Sang
Ling Sang
WHWeiqun He
Weiqun He
SCSibei Chen
Sibei Chen
Yonghao XuYonghao Xu
Yonghao Xu
YLYimin Li
Yimin Li
XLXiaoqing Liu
Xiaoqing Liu
To investigate the value of N-terminal pro-B type natriuretic peptide (NT-proBNP) in predicting the outcome of spontaneous breathing trial (SBT) in ventilated elderly renal dysfunction patients. The clinical data of patients who received mechanical ventilation in the Department of Critical Care Medicine of the First Affiliated Hospital of Guangzhou Medical University, Guangzhou Institute of Respiratory Disease from January 2011 to December 2014 were analyzed retrospectively. AU the patients conformed to the following criteria: age > 65 years, endogenous creatinine clearance rate (CCr) < 60 mL×min(-1)×1.73 m(-2), the duration of mechanical ventilation > 72 hours and undergone at least one SBT. The patients were assigned to a SBT success group and a SBT failure group according to the outcome of first SBT. The following factors were recorded: gender, age, the underlying disease [chronic obstructive pulmonary disease (COPD), heart failure (HF) and others], body mass index (BMI), serum pre-albumin (pre-ALB), and acute physiology and chronic health evaluation II (APACHE II) score, CCr and the concentration of the plasma NT-proBNP before SBT. Receiver operator characteristic curve (ROC) was plotted, and the predict value of NT-proBNP for the outcome of SBT in elder patients with kidney dysfunction was determined. A total of 58 patients with complete data were enrolled, with 41 cases in SBT success group, and 17 in SBT failure group. There were no significant differences in gender [male/female (cases): 26/15 vs. 13/4, χ (2) = 0.930, P = 0.335], age (years: 70.2±7.4 vs. 74.6±10.1, t = 0.833, P = 0.339), the stratification of underlying diseases [COPD/HF/COPD+HF/others (cases): 15/9/13/4 vs. 7/3/5/2, χ (2) = 0.242, P = 0.971], BMI (kg/m(2): 25.2±11.3 vs. 27.4±6.43, t = 1.038, P = 0.221), pre-ALB (mg/L: 201.0±13.2 vs. 189.0±7.6, t = 0.688, P = 0.519), and APACHE II score (12.2±3.2 vs. 13.5±6.3, t = 1.482, P = 0.147) and CCr (mL×min(-1)×1.73 m(-2): 51.3±7.7 vs. 54.2±6.4, t = 0.711, P = 0.487) before SBT between SBT success group and SBT failure group. The concentration of plasma NT-proBNP in SBT failure group was significantly higher than that of the SBT success group (μg/L: 4.162±1.128 vs. 2.284±1.399, t = 4.905, P = 0.000). The area under ROC curve for plasma NT-proBNP in predicting successful SBT among elder patients with kidney dysfunction was 0.878, with 95% confidence interval (95%CI) 0.786 - 0.970. The cut-off method was used, and it was identified that the concentration of NT-proBNP < 3.350 μg/L as a predictor for successful SBT, with sensitivity of 82.4%, specificity of 87.8%, positive prediction value of 88.1% and negative predictive value of 76.5%. The concentration of plasma NT-proBNP may increase in elderly kidney dysfunction patients undergoing ventilation, and NT-proBNP < 3.350 μg/L can serve as a good predictor for SBT success.