2 papers
cs.LG2022
Self-supervised Learning for Heterogeneous Graph via Structure Information based on Metapath
Shuai Ma, Jian-wei Liu, Xin Zuo
graph neural networks (GNNs) are the dominant paradigm for modeling and handling graph structure data by learning universal node representation. The traditional way of training GNN…
cs.CL2022
TraceNet: Tracing and Locating the Key Elements in Sentiment Analysis
Qinghua Zhao, Shuai Ma
In this paper, we study sentiment analysis task where the outcomes are mainly contributed by a few key elements of the inputs. Motivated by the two-streams hypothesis, we propose a…