activity
20172021
most citedAdam revisited: a weighted past gradients perspective

51 citations · 190 across the 10 of their papers we have counts for

collaborators

12 papers

cs.SI2021

Neural PathSim for Inductive Similarity Search in Heterogeneous Information Networks

Wenyi Xiao, Huan Zhao, Vincent W. Zheng +1

PathSim is a widely used meta-path-based similarity in heterogeneous information networks. Numerous applications rely on the computation of PathSim, including similarity search and…

cs.LG2021

Differentially Private Federated Knowledge Graphs Embedding

Hao Peng, Haoran Li, Yangqiu Song +2

Knowledge graph embedding plays an important role in knowledge representation, reasoning, and data mining applications. However, for multiple cross-domain knowledge graphs, state-o…

cs.LG202151 cited

Adam revisited: a weighted past gradients perspective

Hui Zhong, Zaiyi Chen, Chuan Qin +4

Adaptive learning rate methods have been successfully applied in many fields, especially in training deep neural networks. Recent results have shown that adaptive methods with expo…

cs.SI20204 cited

Social Explorative Attention based Recommendation for Content Distribution Platforms

Wenyi Xiao, Huan Zhao, Haojie Pan +3

In modern social media platforms, an effective content recommendation should benefit both creators to bring genuine benefits to them and consumers to help them get really interesti…

cs.CR202012 cited

Privacy Threats Against Federated Matrix Factorization

Dashan Gao, Ben Tan, Ce Ju +2

Matrix Factorization has been very successful in practical recommendation applications and e-commerce. Due to data shortage and stringent regulations, it can be hard to collect suf…

cs.SI2020

Vertex-reinforced Random Walk for Network Embedding

Wenyi Xiao, Huan Zhao, Vincent W. Zheng +1

In this paper, we study the fundamental problem of random walk for network embedding. We propose to use non-Markovian random walk, variants of vertex-reinforced random walk (VRRW),…