Search Results for author: Libin Yang

Found 7 papers, 2 papers with code

General2Specialized LLMs Translation for E-commerce

no code implementations6 Mar 2024 Kaidi Chen, Ben Chen, Dehong Gao, Huangyu Dai, Wen Jiang, Wei Ning, Shanqing Yu, Libin Yang, Xiaoyan Cai

Existing Neural Machine Translation (NMT) models mainly handle translation in the general domain, while overlooking domains with special writing formulas, such as e-commerce and legal documents.

Machine Translation NMT +1

EdgeNet : Encoder-decoder generative Network for Auction Design in E-commerce Online Advertising

no code implementations9 May 2023 Guangyuan Shen, Shengjie Sun, Dehong Gao, Libin Yang, Yongping Shi, Wei Ning

We present a new encoder-decoder generative network dubbed EdgeNet, which introduces a novel encoder-decoder framework for data-driven auction design in online e-commerce advertising.

Fast Heterogeneous Federated Learning with Hybrid Client Selection

no code implementations10 Aug 2022 Guangyuan Shen, Dehong Gao, Duanxiao Song, Libin Yang, Xukai Zhou, Shirui Pan, Wei Lou, Fang Zhou

We present a novel clustering-based client selection scheme to accelerate the FL convergence by variance reduction.

Clustering Federated Learning

Variance-Reduced Heterogeneous Federated Learning via Stratified Client Selection

no code implementations15 Jan 2022 Guangyuan Shen, Dehong Gao, Libin Yang, Fang Zhou, Duanxiao Song, Wei Lou, Shirui Pan

However, due to the large variance of the selected subset's update, prior selection approaches with a limited sampling ratio cannot perform well on convergence and accuracy in heterogeneous FL.

Federated Learning

CoDetect: Financial Fraud Detection With Anomaly Feature Detection

no code implementations IEEE Access 2018 DONGXU HUANG, DEJUN MU, Libin Yang, AND XIAOYAN CAI

In this paper, we propose a novel fraud detection framework, CoDetect, which can leverage both network information and feature information for financial fraud detection.

Anomaly Detection Fraud Detection

Identifying Highly Correlated Stocks Using the Last Few Principal Components

2 code implementations11 Dec 2015 Libin Yang, William Rea, and Alethea Rea

We show that the last few components in principal component analysis of the correlation matrix of a group of stocks may contain useful financial information by identifying highly correlated pairs or larger groups of stocks.

Cannot find the paper you are looking for? You can Submit a new open access paper.