338 citations · 472 across the 43 of their papers we have counts for
8 papers · 1 filter
Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms
Qi Liu, Zheng Gong, Zhenya Huang +5
Machine learning algorithms have become ubiquitous in a number of applications (e.g. image classification). However, due to the insufficient measurement of traditional metrics (e.g…
UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
Yazheng Yang, Yuqi Wang, Guang Liu +2
Recent advancements in NLP have witnessed the groundbreaking impact of pretrained models, yielding impressive outcomes across various tasks. This study seeks to extend the power of…
TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
Mingyue Cheng, Xiaoyu Tao, Zhiding Liu +4
Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate…
FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification
Mingyue Cheng, Qi Liu, Zhiding Liu +3
Deep learning-based algorithms, e.g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task. Nevertheless, they suffer from the…
GraphMI: Extracting Private Graph Data from Graph Neural Networks
Zaixi Zhang, Qi Liu, Zhenya Huang +4
As machine learning becomes more widely used for critical applications, the need to study its implications in privacy turns to be urgent. Given access to the target model and auxil…
Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective
Likang Wu, Zhi Li, Hongke Zhao +2
In the online innovation market, the fund-raising performance of the start-up project is a concerning issue for creators, investors and platforms. Unfortunately, existing studies a…