no code implementations • 24 Apr 2024 • Hui Chen, Hengyu Liu, Zhangkai Wu, Xuhui Fan, Longbing Cao
While deep neural networks (DNNs) based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing methods for federated learning (FL) suffer from efficient systematic uncertainty quantification.
no code implementations • 17 Mar 2024 • Chenxin Li, Hengyu Liu, Yifan Liu, Brandon Y. Feng, Wuyang Li, Xinyu Liu, Zhen Chen, Jing Shao, Yixuan Yuan
In a nutshell, Endora marks a notable breakthrough in the deployment of generative AI for clinical endoscopy research, setting a substantial stage for further advances in medical content generation.
no code implementations • 27 Sep 2023 • Hui Chen, Hengyu Liu, Longbing Cao, Tiancheng Zhang
BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the statistical heterogeneity of client data.
no code implementations • 24 May 2023 • Jiayan Guo, Lun Du, Hengyu Liu, Mengyu Zhou, Xinyi He, Shi Han
In this study, we conduct an extensive investigation to assess the proficiency of LLMs in comprehending graph data, employing a diverse range of structural and semantic-related tasks.
no code implementations • 24 May 2023 • Chongjian Yue, Xinrun Xu, Xiaojun Ma, Lun Du, Hengyu Liu, Zhiming Ding, Yanbing Jiang, Shi Han, Dongmei Zhang
We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports.
no code implementations • 15 May 2023 • Shuhang Tan, Hengyu Liu, Zhiling Wang
Although matching features between different media is challenging, we believe cross-media is the tendency for AV relocalization since its low cost and accuracy can be comparable to the same-sensor-based methods.
no code implementations • 17 Feb 2023 • Hengyu Liu, Tiancheng Zhang, Fan Li, Minghe Yu, Ge Yu
To better model students' exercise responses, we proposed a logarithmic linear model with three interactive strategies, which models students' exercise responses by considering the relationship among students' knowledge status, knowledge concept, and problems.
no code implementations • 25 Aug 2022 • Hengyu Liu, Qiang Fu, Lun Du, Tiancheng Zhang, Ge Yu, Shi Han, Dongmei Zhang
Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training.
no code implementations • 25 Feb 2022 • Chongjian Yue, Lun Du, Qiang Fu, Wendong Bi, Hengyu Liu, Yu Gu, Di Yao
The Temporal Link Prediction task of WSDM Cup 2022 expects a single model that can work well on two kinds of temporal graphs simultaneously, which have quite different characteristics and data properties, to predict whether a link of a given type will occur between two given nodes within a given time span.
1 code implementation • 29 Oct 2021 • Lun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma, Hengyu Liu, Shi Han, Dongmei Zhang
For node-level tasks, GNNs have strong power to model the homophily property of graphs (i. e., connected nodes are more similar) while their ability to capture the heterophily property is often doubtful.