Search Results for author: Tao Xiong

Found 14 papers, 1 papers with code

sqSGD: Locally Private and Communication Efficient Federated Learning

no code implementations21 Jun 2022 Yan Feng, Tao Xiong, Ruofan Wu, LingJuan Lv, Leilei Shi

In addition, with fixed privacy and communication level, the performance of sqSGD significantly dominates that of various baseline algorithms.

Federated Learning Privacy Preserving +1

SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing

no code implementations3 Jul 2021 Hui Li, Xing Fu, Ruofan Wu, Jinyu Xu, Kai Xiao, xiaofu Chang, Weiqiang Wang, Shuai Chen, Leilei Shi, Tao Xiong, Yuan Qi

Deep learning provides a promising way to extract effective representations from raw data in an end-to-end fashion and has proven its effectiveness in various domains such as computer vision, natural language processing, etc.

Management Product Recommendation

Practical Locally Private Federated Learning with Communication Efficiency

no code implementations1 Jan 2021 Yan Feng, Tao Xiong, Ruofan Wu, Yuan Qi

We also initialize a discussion about the role of quantization and perturbation in FL algorithm design with privacy and communication constraints.

Federated Learning Privacy Preserving +1

Memory Augmented Design of Graph Neural Networks

no code implementations1 Jan 2021 Tao Xiong, Liang Zhu, Ruofan Wu, Yuan Qi

Specifically, we allow every node in the original graph to interact with a group of memory nodes.

Node Classification

Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks

1 code implementation18 Mar 2019 Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue

The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description.

Sensitivity based Neural Networks Explanations

no code implementations3 Dec 2018 Enguerrand Horel, Virgile Mison, Tao Xiong, Kay Giesecke, Lidia Mangu

Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes".

Interval Forecasting of Electricity Demand: A Novel Bivariate EMD-based Support Vector Regression Modeling Framework

no code implementations15 Jun 2014 Tao Xiong, Yukun Bao, Zhongyi Hu

Highly accurate interval forecasting of electricity demand is fundamental to the success of reducing the risk when making power system planning and operational decisions by providing a range rather than point estimation.

regression Time Series

Does Restraining End Effect Matter in EMD-Based Modeling Framework for Time Series Prediction? Some Experimental Evidences

no code implementations11 Jan 2014 Tao Xiong, Yukun Bao, Zhongyi Hu

Following the "decomposition-and-ensemble" principle, the empirical mode decomposition (EMD)-based modeling framework has been widely used as a promising alternative for nonlinear and nonstationary time series modeling and prediction.

Time Series Prediction

Multi-Step-Ahead Time Series Prediction using Multiple-Output Support Vector Regression

no code implementations11 Jan 2014 Yukun Bao, Tao Xiong, Zhongyi Hu

As a well-known intelligent algorithm, the standard formulation of Support Vector Regression (SVR) could be taken for multi-step-ahead time series prediction, only relying either on iterated strategy or direct strategy.

regression Time Series Prediction

Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting

no code implementations9 Jan 2014 Tao Xiong, Yukun Bao, Zhongyi Hu

In terms of statistical criteria, we compare the out-of-sample forecasting using goodness-of-forecast measures and testing approaches.

Time Series

A PSO and Pattern Search based Memetic Algorithm for SVMs Parameters Optimization

no code implementations9 Jan 2014 Yukun Bao, Zhongyi Hu, Tao Xiong

Addressing the issue of SVMs parameters optimization, this study proposes an efficient memetic algorithm based on Particle Swarm Optimization algorithm (PSO) and Pattern Search (PS).

Beyond One-Step-Ahead Forecasting: Evaluation of Alternative Multi-Step-Ahead Forecasting Models for Crude Oil Prices

no code implementations8 Jan 2014 Tao Xiong, Yukun Bao, Zhongyi Hu

An accurate prediction of crude oil prices over long future horizons is challenging and of great interest to governments, enterprises, and investors.

PSO-MISMO Modeling Strategy for Multi-Step-Ahead Time Series Prediction

no code implementations31 Dec 2013 Yukun Bao, Tao Xiong, Zhongyi Hu

Multi-step-ahead time series prediction is one of the most challenging research topics in the field of time series modeling and prediction, and is continually under research.

Time Series Prediction

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