activity
20142022
most citedOn the Variance of the Adaptive Learning Rate and Beyond

607 citations · 2.2k across the 78 of their papers we have counts for

collaborators
Showing cs.SIShow all

6 papers · 1 filter

cs.SI2020★ 2 cited

GCN for HIN via Implicit Utilization of Attention and Meta-paths

Di Jin, Zhizhi Yu, Dongxiao He +3

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research att…

cs.SI2020★ 29 cited

Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark

Carl Yang, Yuxin Xiao, Yu Zhang +2

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic super…

cs.SI2020

cube2net: Efficient Query-Specific Network Construction with Data Cube Organization

Carl Yang, Mengxiong Liu, Frank He +2

Networks are widely used to model objects with interactions and have enabled various downstream applications. However, in the real world, network mining is often done on particular…

cs.SI2020★ 99 cited

Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction

Aravind Sankar, Xinyang Zhang, Adit Krishnan +1

Recent years have witnessed tremendous interest in understanding and predicting information spread on social media platforms such as Twitter, Facebook, etc. Existing diffusion pred…

cs.SI2019★ 4 cited

Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders

Carl Yang, Jieyu Zhang, Haonan Wang +5

While node semantics have been extensively explored in social networks, little research attention has been paid to profile edge semantics, i.e., social relations. Ideal edge semant…

cs.SI2019★ 6 cited

CubeNet: Multi-Facet Hierarchical Heterogeneous Network Construction, Analysis, and Mining

Carl Yang, Dai Teng, Siyang Liu +8

Due to the ever-increasing size of data, construction, analysis and mining of universal massive networks are becoming forbidden and meaningless. In this work, we outline a novel fr…