activity
20162022
most citedLayer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

87 citations · 247 across the 13 of their papers we have counts for

collaborators

16 papers

cs.CL20222 cited

Empowering Language Models with Knowledge Graph Reasoning for Question Answering

Ziniu Hu, Yichong Xu, Wenhao Yu +5

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external kn…

cs.CL2021

Relation-Guided Pre-Training for Open-Domain Question Answering

Ziniu Hu, Yizhou Sun, Kai-Wei Chang

Answering complex open-domain questions requires understanding the latent relations between involving entities. However, we found that the existing QA datasets are extremely imbala…

cs.CL2021

Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning

Da Yin, Liunian Harold Li, Ziniu Hu +2

Commonsense is defined as the knowledge that is shared by everyone. However, certain types of commonsense knowledge are correlated with culture and geographic locations and they ar…

cs.LG202016 cited

Motif-Driven Contrastive Learning of Graph Representations

Shichang Zhang, Ziniu Hu, Arjun Subramonian +1

Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive…

cs.LG202071 cited

GPT-GNN: Generative Pre-Training of Graph Neural Networks

Ziniu Hu, Yuxiao Dong, Kuansan Wang +2

Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs usually requires abundant task-specific labeled data, w…

cs.LG202030 cited

Heterogeneous Graph Transformer

Ziniu Hu, Yuxiao Dong, Kuansan Wang +1

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all…