most citedMulti-Task Representation Learning with Multi-View Graph Convolutional Networks

43 citations · 49 across the 6 of their papers we have counts for

collaborators

6 papers

cs.SI2021

Multi-Stage Network Embedding for Exploring Heterogeneous Edges

Hong Huang, Yu Song, Fanghua Ye +3

The relationships between objects in a network are typically diverse and complex, leading to the heterogeneous edges with different semantic information. In this paper, we focus on…

cs.IR20212 cited

Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations

Yu Song, Jianxun Lian, Shuai Sun +4

User interest exploration is an important and challenging topic in recommender systems, which alleviates the closed-loop effects between recommendation models and user-item interac…

cs.CL20211 cited

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction

Zhexue Chen, Hong Huang, Bang Liu +2

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining…

cs.SI2021

Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder

Lu Wang, Yu Song, Hong Huang +3

In the real world, networks often contain multiple relationships among nodes, manifested as the heterogeneity of the edges in the networks. We convert the heterogeneous networks in…

cs.SI202143 cited

Multi-Task Representation Learning with Multi-View Graph Convolutional Networks

Hong Huang, Yu Song, Yao Wu +3

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform th…

cs.CY20193 cited

Estimating Socioeconomic Status via Temporal-Spatial Mobility Analysis -- A Case Study of Smart Card Data

Shichang Ding, Hong Huang, Tao Zhao +1

The notion of socioeconomic status (SES) of a person or family reflects the corresponding entity's social and economic rank in society. Such information may help applications like…