93 citations · 165 across the 9 of their papers we have counts for
10 papers
AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System
Zhirong Xu, Shiyang Wen, Junshan Wang +8
Graph embedding based retrieval has become one of the most popular techniques in the information retrieval community and search engine industry. The classical paradigm mainly relie…
TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
Lun Du, Fei Gao, Xu Chen +5
Tabular data are ubiquitous for the widespread applications of tables and hence have attracted the attention of researchers to extract underlying information. One of the critical p…
TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
Xu Chen, Junshan Wang, Kunqing Xie
With the rapid growth of traffic sensors deployed, a massive amount of traffic flow data are collected, revealing the long-term evolution of traffic flows and the gradual expansion…
Learning Node Representations from Noisy Graph Structures
Junshan Wang, Ziyao Li, Qingqing Long +3
Learning low-dimensional representations on graphs has proved to be effective in various downstream tasks. However, noises prevail in real-world networks, which compromise networks…
EPNE: Evolutionary Pattern Preserving Network Embedding
Junshan Wang, Yilun Jin, Guojie Song +1
Information networks are ubiquitous and are ideal for modeling relational data. Networks being sparse and irregular, network embedding algorithms have caught the attention of many…
Streaming Graph Neural Networks via Continual Learning
Junshan Wang, Guojie Song, Yi Wu +1
Graph neural networks (GNNs) have achieved strong performance in various applications. In the real world, network data is usually formed in a streaming fashion. The distributions o…