Search Results for author: Junbo Zhang

Found 38 papers, 18 papers with code

MLPST: MLP is All You Need for Spatio-Temporal Prediction

no code implementations23 Sep 2023 Zijian Zhang, Ze Huang, Zhiwei Hu, Xiangyu Zhao, Wanyu Wang, Zitao Liu, Junbo Zhang, S. Joe Qin, Hongwei Zhao

To accomplish the above goals, we propose an intuitive and novel framework, MLPST, a pure multi-layer perceptron architecture for traffic prediction.

Traffic Prediction

Spatio-Temporal Contrastive Self-Supervised Learning for POI-level Crowd Flow Inference

no code implementations6 Sep 2023 Songyu Ke, Ting Li, Li Song, Yanping Sun, Qintian Sun, Junbo Zhang, Yu Zheng

To address these challenges, we recast the crowd flow inference problem as a self-supervised attributed graph representation learning task and introduce a novel Contrastive Self-learning framework for Spatio-Temporal data (CSST).

Contrastive Learning Graph Representation Learning +2

AutoSTL: Automated Spatio-Temporal Multi-Task Learning

no code implementations16 Apr 2023 Zijian Zhang, Xiangyu Zhao, Hao Miao, Chunxu Zhang, Hongwei Zhao, Junbo Zhang

To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly.

Multi-Task Learning

Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey

no code implementations25 Mar 2023 Guangyin Jin, Yuxuan Liang, Yuchen Fang, Zezhi Shao, Jincai Huang, Junbo Zhang, Yu Zheng

STGNNs enable the extraction of complex spatio-temporal dependencies by integrating graph neural networks (GNNs) and various temporal learning methods.


CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP

no code implementations8 Mar 2023 Junbo Zhang, Runpei Dong, Kaisheng Ma

Training a 3D scene understanding model requires complicated human annotations, which are laborious to collect and result in a model only encoding close-set object semantics.

Scene Understanding Semantic Segmentation

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

3 code implementations16 Dec 2022 Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages.

Few-Shot 3D Point Cloud Classification Knowledge Distillation +1

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

1 code implementation7 Dec 2022 Jiahao Ji, Jingyuan Wang, Chao Huang, Junjie Wu, Boren Xu, Zhenhe Wu, Junbo Zhang, Yu Zheng

ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods.

Robust Traffic Prediction Self-Supervised Learning +2

AirFormer: Predicting Nationwide Air Quality in China with Transformers

1 code implementation29 Nov 2022 Yuxuan Liang, Yutong Xia, Songyu Ke, Yiwei Wang, Qingsong Wen, Junbo Zhang, Yu Zheng, Roger Zimmermann

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth.

Language-Assisted 3D Feature Learning for Semantic Scene Understanding

1 code implementation25 Nov 2022 Junbo Zhang, Guofan Fan, Guanghan Wang, Zhengyuan Su, Kaisheng Ma, Li Yi

To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions.

Descriptive Instance Segmentation +4

Contrastive Deep Supervision

1 code implementation12 Jul 2022 Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma

The success of deep learning is usually accompanied by the growth in neural network depth.

Contrastive Learning Fine-Grained Image Classification +3

Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views

1 code implementation CVPR 2022 Junbo Zhang, Kaisheng Ma

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable.

Contrastive Learning Data Augmentation

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

no code implementations31 May 2022 Gaode Chen, Yijun Su, Xinghua Zhang, Anmin Hu, Guochun Chen, Siyuan Feng, Ji Xiang, Junbo Zhang, Yu Zheng

To address the above challenging problems, we propose a novel Cross-city Federated Transfer Learning framework (CcFTL) to cope with the data insufficiency and privacy problems.

Transfer Learning

Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation

1 code implementation14 Apr 2022 Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Quyang Pan, Junbo Zhang, Zeju Li, Qingxiang Liu

Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead.

Federated Learning Privacy Preserving

Spatio-Temporal Dynamic Graph Relation Learning for Urban Metro Flow Prediction

no code implementations6 Apr 2022 Peng Xie, Minbo Ma, Tianrui Li, Shenggong Ji, Shengdong Du, Zeng Yu, Junbo Zhang

Second, we employ a dynamic graph relationship learning module to learn dynamic spatial relationships between metro stations without a predefined graph adjacency matrix.

Management Relational Reasoning +1

HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting

no code implementations22 Jan 2022 Minbo Ma, Peng Xie, Fei Teng, Tianrui Li, Bin Wang, Shenggong Ji, Junbo Zhang

In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations.

Graph Learning Self-Learning +3

Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network

1 code implementation8 Oct 2021 Xiyue Zhang, Chao Huang, Yong Xu, Lianghao Xia, Peng Dai, Liefeng Bo, Junbo Zhang, Yu Zheng

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment.

Traffic Prediction

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

2 code implementations13 Jun 2021 Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10, 000 hours of high quality labeled audio suitable for supervised training, and 40, 000 hours of total audio suitable for semi-supervised and unsupervised training.

speech-recognition Speech Recognition

speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment

2 code implementations3 Apr 2021 Junbo Zhang, Zhiwen Zhang, Yongqing Wang, Zhiyong Yan, Qiong Song, YuKai Huang, Ke Li, Daniel Povey, Yujun Wang

This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children.

Phone-level pronunciation scoring speech-recognition

Fairness and Accuracy in Federated Learning

no code implementations18 Dec 2020 Wei Huang, Tianrui Li, Dexian Wang, Shengdong Du, Junbo Zhang

An appropriate weight selection algorithm that combines the information quantity of training accuracy and training frequency to measure the weights is proposed.

Fairness Federated Learning

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics

1 code implementation28 Feb 2020 Yuxuan Liang, Kun Ouyang, Yiwei Wang, Ye Liu, Junbo Zhang, Yu Zheng, David S. Rosenblum

This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods.

Tensor Decomposition

Federated Extra-Trees with Privacy Preserving

no code implementations18 Feb 2020 Yang Liu, Mingxin Chen, Wenxi Zhang, Junbo Zhang, Yu Zheng

It is commonly observed that the data are scattered everywhere and difficult to be centralized.

BIG-bench Machine Learning Privacy Preserving

Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning

1 code implementation KDD '19 2019 Zheyi Pan, Yuxuan Liang, Weifeng Wang, Yong Yu, Yu Zheng, Junbo Zhang

Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging because of two aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) diversity of such spatiotemporal correlations, which vary from location to location and depend on the surrounding geographical information, e. g., points of interests and road networks.

Graph Attention Meta-Learning +3

DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction

1 code implementation ACL 2019 Huaishao Luo, Tianrui Li, Bing Liu, Junbo Zhang

This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction.

Aspect-Based Sentiment Analysis (ABSA) Sentiment Classification +1

Federated Forest

no code implementations24 May 2019 Yang Liu, Yingting Liu, Zhijie Liu, Junbo Zhang, Chuishi Meng, Yu Zheng

In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i. e., achieving the same level of accuracy as the non-privacy-preserving approach.

BIG-bench Machine Learning Privacy Preserving

Arbitrage of Energy Storage in Electricity Markets with Deep Reinforcement Learning

no code implementations28 Apr 2019 Hanchen Xu, Xiao Li, Xiangyu Zhang, Junbo Zhang

In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty.

reinforcement-learning Reinforcement Learning (RL)

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

no code implementations19 Mar 2019 Junkai Sun, Junbo Zhang, Qiaofei Li, Xiuwen Yi, Yuxuan Liang, Yu Zheng

In this paper, we formulate crowd flow forecasting in irregular regions as a spatio-temporal graph (STG) prediction problem in which each node represents a region with time-varying flows.

UrbanFM: Inferring Fine-Grained Urban Flows

1 code implementation6 Feb 2019 Yuxuan Liang, Kun Ouyang, Lin Jing, Sijie Ruan, Ye Liu, Junbo Zhang, David S. Rosenblum, Yu Zheng

In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations.

Fine-Grained Urban Flow Inference

HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting

no code implementations28 Sep 2018 Zheyi Pan, Yuxuan Liang, Junbo Zhang, Xiuwen Yi, Yong Yu, Yu Zheng

In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models.

Spatio-Temporal Forecasting Time Series +1

Attention-based End-to-End Models for Small-Footprint Keyword Spotting

2 code implementations29 Mar 2018 Changhao Shan, Junbo Zhang, Yujun Wang, Lei Xie

In this paper, we propose an attention-based end-to-end neural approach for small-footprint keyword spotting (KWS), which aims to simplify the pipelines of building a production-quality KWS system.

Small-Footprint Keyword Spotting

Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model

1 code implementation27 Mar 2018 Ke Wang, Junbo Zhang, Yujun Wang, Lei Xie

Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities.

Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition

1 code implementation27 Mar 2018 Ke Wang, Junbo Zhang, Sining Sun, Yujun Wang, Fei Xiang, Lei Xie

First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset.

Robust Speech Recognition Speech Dereverberation +1

Attention-Based End-to-End Speech Recognition on Voice Search

no code implementations22 Jul 2017 Changhao Shan, Junbo Zhang, Yujun Wang, Lei Xie

Previous attempts have shown that applying attention-based encoder-decoder to Mandarin speech recognition was quite difficult due to the logographic orthography of Mandarin, the large vocabulary and the conditional dependency of the attention model.

L2 Regularization Language Modelling +2

Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks

no code implementations10 Jan 2017 Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi, Tianrui Li

We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i. e. inflow and outflow) in each and every region of a city.


Parallel Large-Scale Attribute Reduction on Cloud Systems

no code implementations6 Oct 2016 Junbo Zhang, Tianrui Li, Yi Pan

The rapid growth of emerging information technologies and application patterns in modern society, e. g., Internet, Internet of Things, Cloud Computing and Tri-network Convergence, has caused the advent of the era of big data.

Cloud Computing feature selection

Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

4 code implementations1 Oct 2016 Junbo Zhang, Yu Zheng, Dekang Qi

The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region.

Crowd Flows Prediction Management

ST-MVL: Filling Missing Values in Geo-Sensory Time Series Data

no code implementations IJCAI 2016 2016 Xiuwen Yi, Yu Zheng, Junbo Zhang, Tianrui Li

In this paper, we propose a spatio-temporal multi-view-based learning (ST-MVL) method to collectively fill missing readings in a collection of geosensory time series data, considering 1) the temporal correlation between readings at different timestamps in the same series and 2) the spatial correlation between different time series.

Collaborative Filtering Multivariate Time Series Imputation +3

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