Walking With Attention: Self-Guided Walking for Heterogeneous Graph Embedding

Yunzhi Hao, Xinchao Wang, Xingen Wang, Xinyu Wang, Chun Chen, Mingli Song

Abstract

Heterogeneous graph embedding aims at learning low-dimensional representations from a graph featuring nodes and edges of diverse natures, and meanwhile preserving the underlying topology. Existing approaches along this line have largely relied on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">meta-paths</i> , which are by nature hand-crafted and pre-defined transition rules, so as to explore the semantics of a graph. Despite the promising results, defining meta-paths requires domain knowledge, and thus when the test distribution deviates from the priors, such methods are prone to errors. In this paper, we propose a self-learning scheme for heterogeneous graph embedding, termed as self-guided walk (SILK), that bypasses meta-paths and learns adaptive attentions for node walking. SILK assumes no prior knowledge or annotation is provided, and conducts a customized random walk to encode the contexts of the heterogeneous graph of interest. Specifically, this is achieved via maintaining a dynamically-updated <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">guidance matrix</i> that records the node-conditioned transition potentials. Experimental results on four real-world datasets demonstrate that SILK significantly outperforms state-of-the-art methods.
BibTeX
@article{hao2022walking,
  author = {Yunzhi Hao and Xinchao Wang and Xingen Wang and Xinyu Wang and Chun Chen and Mingli Song},
  title = {{Walking With Attention: Self-Guided Walking for Heterogeneous Graph Embedding}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2022},
  url = {https://openreview.net/forum?id=K0DxbXvlHj},
}

Loading related content...

Figure