activity
20162023
most citedWhen Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities

338 citations · 472 across the 43 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG20232 cited

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…

cs.LG2023

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…

cs.LG2023

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…

cs.LG20232 cited

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…

cs.LG20213 cited

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…

cs.LG20211 cited

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…