.png){kind=icon}
Return
Subgraph Gaussian Embedding Contrast for Self-supervised Graph Representation Learning
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-06106-5_25.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph Representation Learning (GRL) is a fundamental task in machine learning, aiming to encode high-dimensional graph-structured data into low-dimensional vectors. Self-Supervised Learning (SSL) methods are widely used in GRL because they can avoid expensive human annotation. In this work, we propose a novel Subgraph Gaussian Embedding Contrast (SubGEC) method. Our approach introduces a subgraph Gaussian embedding module, which adaptively maps subgraphs to a structured Gaussian space, ensuring the preservation of input subgraph characteristics while generating subgraphs with a controlled distribution. We then employ optimal transport distances, more precisely the Wasserstein and Gromov-Wasserstein distances, to effectively measure the similarity between subgraphs, enhancing the robustness of the contrastive learning process. Extensive experiments across multiple benchmarks demonstrate that SubGEC outperforms or presents competitive performance against state-of-the-art approaches. Our findings provide insights into the design of SSL methods for GRL, emphasizing the importance of the distribution of the generated contrastive pairs.
Keywords:
Subgraph Gaussian embeddings
graph representation learning
self-supervised learning
optimal transport
Journal
M
IF:
0
Papers:
25
Citations:
0
Organization
Cited Papers
.png){kind=icon}
Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating
OAAI
OAAIShareSaveShareSaveShareSaveShareSave
View more