activity
20202022
most citedTopology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs

12 citations · 14 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG20221 cited

Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation

Huarui He, Jie Wang, Zhanqiu Zhang +1

Deep graph neural networks (GNNs) have been shown to be expressive for modeling graph-structured data. Nevertheless, the over-stacked architecture of deep graph models makes it dif…

cs.CL2022

Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings

Jie Wang, Zhanqiu Zhang, Zhihao Shi +3

Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing s…

cs.AI20221 cited

Rethinking Graph Convolutional Networks in Knowledge Graph Completion

Zhanqiu Zhang, Jie Wang, Jieping Ye +1

Graph convolutional networks (GCNs) -- which are effective in modeling graph structures -- have been increasingly popular in knowledge graph completion (KGC). GCN-based KGC models…

cs.CL2021

Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021

Jianyu Cai, Jiajun Chen, Taoxing Pan +2

Link prediction in large-scale knowledge graphs has gained increasing attention recently. The OGB-LSC team presented OGB Large-Scale Challenge (OGB-LSC), a collection of three real…

cs.LG202112 cited

Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs

Jiajun Chen, Huarui He, Feng Wu +1

Inductive link prediction -- where entities during training and inference stages can be different -- has been shown to be promising for completing continuously evolving knowledge g…

cs.LG2021

On Explainability of Graph Neural Networks via Subgraph Explorations

Hao Yuan, Haiyang Yu, Jie Wang +2

We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explainin…