Zhiyi Chen

Zhiyi Chen

Auto-generated profile, based on publicly available information

Zhiyi Chen

Georgia Institute of Technology, Atlanta, Georgia, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
13 June 2023 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
PLPeng Li
Peng Li
ZCZhiyi Chen
Zhiyi Chen
XCXu Chu
Xu Chu
KRKexin Rong
Kexin Rong
Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time-consuming, often requiring the expertise of domain experts. Existing automated machine learning (AutoML) frameworks claim to automate data preprocessing. However, they often use a restricted search space of data preprocessing pipelines which limits the potential performance gains, and they are often too slow as they require training the ML model multiple times. In this paper, we propose DiffPrep, a method that can automatically and efficiently search for a data preprocessing pipeline for a given tabular dataset and a differentiable ML model such that the performance of the ML model is maximized. We formalize the problem of data preprocessing pipeline search as a bi-level optimization problem. To solve this problem efficiently, we transform and relax the discrete, non-differential search space into a continuous and differentiable one, which allows us to perform the pipeline search using gradient descent with training the ML model only once. Our experiments show that DiffPrep achieves the best test accuracy on 15 out of the 18 real-world datasets evaluated and improves the model's test accuracy by up to 6.6 percentage points.

10 March 2023
Verified
Book Chapter
Closed access
PDF file
ZCZhiyi Chen
Zhiyi Chen
ZBZachary S. Bischof
Zachary S. Bischof
CTCecilia Testart
Cecilia Testart
ADAlberto Dainotti
Alberto Dainotti

12 October 2026
Verified
Conference Paper
Open access
ZCZhiyi Chen
Zhiyi Chen
ZBZachary Bischof
Zachary Bischof
CTCecilia Testart
Cecilia Testart
ADAlberto Dainotti
Alberto Dainotti

12 October 2026
Verified
Conference Paper
Open access
ZCZhiyi Chen
Zhiyi Chen
ZBZachary Bischof
Zachary Bischof
CTCecilia Testart
Cecilia Testart
ADAlberto Dainotti
Alberto Dainotti
Autonomous Systems (ASes) form the backbone of the Internet's routing infrastructure and aggregate diverse network services. In this work, we rethink how network properties are attributed to ASes in light of the broad range of Internet datasets now available, and argue that each property of interest should be represented as its own tag rather than as part of a rigid taxonomy. Guided by this view, we provide principles and a shared, unified data-and-software framework that facilitates systematic, accurate, flexible, and reproducible AS classification by network properties. Empirical analyses and multiple case studies demonstrate its research impact and improvements over existing best practices.