Search Results for author: Hongzhi Wang

Found 34 papers, 6 papers with code

EEML: Ensemble Embedded Meta-learning

no code implementations18 Jun 2022 Geng Li, Boyuan Ren, Hongzhi Wang

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks.

Few-Shot Learning

FIND:Explainable Framework for Meta-learning

no code implementations20 May 2022 Xinyue Shao, Hongzhi Wang, Xiao Zhu, Feng Xiong

Meta-learning is used to efficiently enable the automatic selection of machine learning models by combining data and prior knowledge.

Fairness Meta-Learning

AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning

no code implementations26 Mar 2022 Chunnan Wang, Xingyu Chen, Chengyue Wu, Hongzhi Wang

We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks.

Neural Architecture Search Time Series Forecasting

AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy

1 code implementation24 Jan 2022 Chunnan Wang, Hongzhi Wang, Xiangyu Shi

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments.

Model Compression

TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model

no code implementations9 Jan 2022 Chunnan Wang, Chen Liang, Xiang Chen, Hongzhi Wang

They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results.

Anomaly Detection AutoML +1

ATPFL: Automatic Trajectory Prediction Model Design Under Federated Learning Framework

no code implementations CVPR 2022 Chunnan Wang, Xiang Chen, Junzhe Wang, Hongzhi Wang

Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users.

Federated Learning Trajectory Prediction

Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion

no code implementations10 Dec 2021 Ken C. L. Wong, Hongzhi Wang, Etienne E. Vos, Bianca Zadrozny, Campbell D. Watson, Tanveer Syeda-Mahmood

Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property.


Differentiable Self-Adaptive Learning Rate

no code implementations29 Sep 2021 Bozhou Chen, Hongzhi Wang, Chenmin Ba

Adaptive learning rate has been studied for a long time.

Differentiable Hyper-parameter Optimization

no code implementations29 Sep 2021 Bozhou Chen, Hongzhi Wang, Chenmin Ba

We apply our method for the optimization of various neural network layers' hyper-parameters and compare it with multiple benchmark hyper-parameter optimization models.

BIG-bench Machine Learning

Search For Deep Graph Neural Networks

no code implementations21 Sep 2021 Guosheng Feng, Chunnan Wang, Hongzhi Wang

Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem.


FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search

no code implementations9 Apr 2021 Chunnan Wang, Bozhou Chen, Geng Li, Hongzhi Wang

Recently, some Neural Architecture Search (NAS) techniques are proposed for the automatic design of Graph Convolutional Network (GCN) architectures.

Federated Learning Neural Architecture Search

Approximate Query Processing for Group-By Queries based on Conditional Generative Models

no code implementations8 Jan 2021 Meifan Zhang, Hongzhi Wang

Online sampling chooses samples for the given query at query time, but it requires a long latency.

Data Visualization

Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results

no code implementations15 Oct 2020 Chunnan Wang, Kaixin Zhang, Hongzhi Wang, Bozhou Chen

In recent years, many spatial-temporal graph convolutional network (STGCN) models are proposed to deal with the spatial-temporal network data forecasting problem.

EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective

1 code implementation18 Sep 2020 Zhaochong An, Bozhou Chen, Houde Quan, Qihui Lin, Hongzhi Wang

To solve this problem, in this paper, we propose a general framework, named EM-RBR(embedding and rule-based reasoning), capable of combining the advantages of reasoning based on rules and the state-of-the-art models of embedding.

Knowledge Graph Completion Link Prediction

Automatic Storage Structure Selection for hybrid Workload

no code implementations15 Aug 2020 Hongzhi Wang, Yan Wei, Hao Yan

Therefore, the users of the database need to select the storage engine and design data model according to the workload encountered.

Auto-CASH: Autonomous Classification Algorithm Selection with Deep Q-Network

no code implementations7 Jul 2020 Tianyu Mu, Hongzhi Wang, Chunnan Wang, Zheng Liang

In our work, we present Auto-CASH, a pre-trained model based on meta-learning, to solve the CASH problem more efficiently.

BIG-bench Machine Learning General Classification +2

Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation

1 code implementation6 Jul 2020 Chunnan Wang, Hongzhi Wang, Guosheng Feng, Fei Geng

To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only.

Neural Architecture Search

ConsciousControlFlow(CCF): A Demonstration for conscious Artificial Intelligence

1 code implementation9 Apr 2020 Hongzhi Wang, Bozhou Chen, Yueyang Xu, Kaixin Zhang, Shengwen Zheng

In this demo, we present ConsciousControlFlow(CCF), a prototype system to demonstrate conscious Artificial Intelligence (AI).

LAQP: Learning-based Approximate Query Processing

no code implementations5 Mar 2020 Meifan Zhang, Hongzhi Wang

Querying on big data is a challenging task due to the rapid growth of data amount.

ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning

no code implementations2 Dec 2019 Chunnan Wang, Hongzhi Wang, Chang Zhou, Hanxiao Chen

Motivated by this, we propose ExperienceThinking algorithm to quickly find the best possible hyperparameter configuration of machine learning algorithms within a few configuration evaluations.

BIG-bench Machine Learning Hyperparameter Optimization +1

Auto-Model: Utilizing Research Papers and HPO Techniques to Deal with the CASH problem

no code implementations24 Oct 2019 Chunnan Wang, Hongzhi Wang, Tianyu Mu, Jianzhong Li, Hong Gao

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems.

Hyperparameter Optimization

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

no code implementations22 Aug 2019 Hongzhi Wang, Yijie Yang, Yang song

In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction.

LSTM-based Flow Prediction

no code implementations9 Aug 2019 Hongzhi Wang, Yang song, Shihan Tang

In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed.

Time Series

Predicting Learning Status in MOOCs using LSTM

no code implementations5 Aug 2018 Zhemin Liu, Feng Xiong, Kaifa Zou, Hongzhi Wang

Real-time and open online course resources of MOOCs have attracted a large number of learners in recent years.

General Classification Time Series Classification +1

Error Detection in a Large-Scale Lexical Taxonomy

no code implementations5 Aug 2018 Sifan Liu, Hongzhi Wang

Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets.

Impacts of Dirty Data: and Experimental Evaluation

no code implementations16 Mar 2018 Zhixin Qi, Hongzhi Wang, Jianzhong Li, Hong Gao

Data quality issues have attracted widespread attention due to the negative impacts of dirty data on data mining and machine learning results.

BIG-bench Machine Learning General Classification

Hierarchical Spatial-aware Siamese Network for Thermal Infrared Object Tracking

1 code implementation27 Nov 2017 Xin Li, Qiao Liu, Nana Fan, Zhenyu He, Hongzhi Wang

In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task.

General Classification Thermal Infrared Object Tracking

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