Search Results for author: Xiaoliang Fan

Found 10 papers, 5 papers with code

Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection

no code implementations28 Feb 2024 Xun Huang, Hai Wu, Xin Li, Xiaoliang Fan, Chenglu Wen, Cheng Wang

LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals.

Knowledge Distillation object-detection +1

Urban Region Representation Learning with Attentive Fusion

no code implementations7 Dec 2023 Fengze Sun, Jianzhong Qi, Yanchuan Chang, Xiaoliang Fan, Shanika Karunasekera, Egemen Tanin

Our model is powered by a dual-feature attentive fusion module named DAFusion, which fuses embeddings from different region features to learn higher-order correlations between the regions as well as between the different types of region features.

Representation Learning

INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging

1 code implementation6 Feb 2023 Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, Jianzhong Qi, Chaochao Chen, Longbiao Chen

It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest.

Graph Representation Learning Relation

FedGS: Federated Graph-based Sampling with Arbitrary Client Availability

1 code implementation25 Nov 2022 Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Haibing Jin, Peizhen Yang, Siqi Shen, Cheng Wang

Second, constrained by the far-distance in data distribution of the sampled clients, we further minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias.

Federated Learning

Multi-Graph Fusion Networks for Urban Region Embedding

1 code implementation24 Jan 2022 Shangbin Wu, Xu Yan, Xiaoliang Fan, Shirui Pan, Shichao Zhu, Chuanpan Zheng, Ming Cheng, Cheng Wang

Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.

Crime Prediction

Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting

no code implementations25 Nov 2021 Chuanpan Zheng, Xiaoliang Fan, Shirui Pan, Haibing Jin, Zhaopeng Peng, Zonghan Wu, Cheng Wang, Philip S. Yu

However, this approach failed to explicitly reflect the correlations between different nodes at different time steps, thus limiting the learning capability of graph neural networks.

ConTIG: Continuous Representation Learning on Temporal Interaction Graphs

no code implementations27 Sep 2021 Xu Yan, Xiaoliang Fan, Peizhen Yang, Zonghan Wu, Shirui Pan, Longbiao Chen, Yu Zang, Cheng Wang

Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems.

Dynamic Node Classification Link Prediction +1

GMAN: A Graph Multi-Attention Network for Traffic Prediction

6 code implementations11 Nov 2019 Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, Jianzhong Qi

Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder.

Image Dehazing Traffic Prediction

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