10.1k citations · 10.4k across the 8 of their papers we have counts for
9 papers
When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series
Chen Shao, Yue Wang, Zhenyi Zhu +4
Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant t…
Personalized Federated Learning With Graph
Fengwen Chen, Guodong Long, Zonghan Wu +2
Knowledge sharing and model personalization are two key components in the conceptual framework of personalized federated learning (PFL). Existing PFL methods focus on proposing new…
Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
Chuanpan Zheng, Xiaoliang Fan, Shirui Pan +5
Recent studies have shifted their focus towards formulating traffic forecasting as a spatio-temporal graph modeling problem. Typically, they constructed a static spatial graph at e…
ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
Xu Yan, Xiaoliang Fan, Peizhen Yang +5
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. Existi…
TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting
Zonghan Wu, Da Zheng, Shirui Pan +3
This paper aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial-temporal dependencies for traffic data. For spatial-t…
Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
Zonghan Wu, Shirui Pan, Guodong Long +2
Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings.…