Graph Embedding with Rich Information through Heterogeneous Network
This work addresses the need for more effective graph analysis in social networks by enhancing embedding techniques, though it is incremental as it builds on existing methods by adding text information.
The paper tackles the problem of graph embedding by incorporating rich text information from nodes and edges, which existing methods often ignore, resulting in improved node classification performance with a 10% increase in Micro-F1 and 7% in Macro-F1 on the Cora dataset.
Graph embedding has attracted increasing attention due to its critical application in social network analysis. Most existing algorithms for graph embedding only rely on the typology information and fail to use the copious information in nodes as well as edges. As a result, their performance for many tasks may not be satisfactory. In this paper, we proposed a novel and general framework of representation learning for graph with rich text information through constructing a bipartite heterogeneous network. Specially, we designed a biased random walk to explore the constructed heterogeneous network with the notion of flexible neighborhood. The efficacy of our method is demonstrated by extensive comparison experiments with several baselines on various datasets. It improves the Micro-F1 and Macro-F1 of node classification by 10% and 7% on Cora dataset.