172 citations · 728 across the 26 of their papers we have counts for
13 papers · 1 filter
The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field
Kun Wang, Guohao Li, Shilong Wang +6
Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoot…
LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
Xu Liu, Yutong Xia, Yuxuan Liang +7
Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning in capturing non-linear p…
Graph Neural Processes for Spatio-Temporal Extrapolation
Junfeng Hu, Yuxuan Liang, Zhencheng Fan +3
We study the task of spatio-temporal extrapolation that generates data at target locations from surrounding contexts in a graph. This task is crucial as sensors that collect data a…
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey
Guangyin Jin, Yuxuan Liang, Yuchen Fang +4
With recent advances in sensing technologies, a myriad of spatio-temporal data has been generated and recorded in smart cities. Forecasting the evolution patterns of spatio-tempora…
Do We Really Need Graph Neural Networks for Traffic Forecasting?
Xu Liu, Yuxuan Liang, Chao Huang +4
Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting. While successful, they rely on the message passing scheme of GNNs to est…
DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models
Haomin Wen, Youfang Lin, Yutong Xia +4
Spatio-temporal graph neural networks (STGNN) have emerged as the dominant model for spatio-temporal graph (STG) forecasting. Despite their success, they fail to model intrinsic un…
Periodic Residual Learning for Crowd Flow Forecasting
Chengxin Wang, Yuxuan Liang, Gary Tan
Crowd flow forecasting, which aims to predict the crowds entering or leaving certain regions, is a fundamental task in smart cities. One of the key properties of crowd flow data is…
Structure-Aware Label Smoothing for Graph Neural Networks
Yiwei Wang, Yujun Cai, Yuxuan Liang +5
Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect th…
Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference
Junfeng Hu, Yuxuan Liang, Zhencheng Fan +3
Sensors are the key to environmental monitoring, which impart benefits to smart cities in many aspects, such as providing real-time air quality information to assist human decision…
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?
Xu Liu, Yuxuan Liang, Chao Huang +3
Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements…
Directed Graph Convolutional Network
Zekun Tong, Yuxuan Liang, Changsheng Sun +2
Graph Convolutional Networks (GCNs) have been widely used due to their outstanding performance in processing graph-structured data. However, the undirected graphs limit their appli…
Federated Forest
Yang Liu, Yingting Liu, Zhijie Liu +3
Most real-world data are scattered across different companies or government organizations, and cannot be easily integrated under data privacy and related regulations such as the Eu…
HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
Zheyi Pan, Yuxuan Liang, Junbo Zhang +3
Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality…