activity
20182023
most citedInvestigating and Mitigating Degree-Related Biases in Graph Convolutional Networks

96 citations · 246 across the 9 of their papers we have counts for

collaborators

14 papers

cs.CL20221 cited

Short Text Pre-training with Extended Token Classification for E-commerce Query Understanding

Haoming Jiang, Tianyu Cao, Zheng Li +6

E-commerce query understanding is the process of inferring the shopping intent of customers by extracting semantic meaning from their search queries. The recent progress of pre-tra…

cs.LG2022

DiP-GNN: Discriminative Pre-Training of Graph Neural Networks

Simiao Zuo, Haoming Jiang, Qingyu Yin +3

Graph neural network (GNN) pre-training methods have been proposed to enhance the power of GNNs. Specifically, a GNN is first pre-trained on a large-scale unlabeled graph and then…

cs.LG202114 cited

Semi-Supervised Graph-to-Graph Translation

Tianxiang Zhao, Xianfeng Tang, Xiang Zhang +1

Graph translation is very promising research direction and has a wide range of potential real-world applications. Graph is a natural structure for representing relationship and int…

cs.LG202049 cited

Graph Structure Learning for Robust Graph Neural Networks

Wei Jin, Yao Ma, Xiaorui Liu +3

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, cal…

cs.SI202032 cited

Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps

Xianfeng Tang, Yozen Liu, Neil Shah +3

With the rapid growth and prevalence of social network applications (Apps) in recent years, understanding user engagement has become increasingly important, to provide useful insig…

cs.LG202096 cited

Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks

Xianfeng Tang, Huaxiu Yao, Yiwei Sun +5

Graph Convolutional Networks (GCNs) show promising results for semi-supervised learning tasks on graphs, thus become favorable comparing with other approaches. Despite the remarkab…