TY - GEN
T1 - Subgraph Gaussian Embedding Contrast for Self-supervised Graph Representation Learning
AU - Xie, Shifeng
AU - Einizade, Aref
AU - Giraldo, Jhony H.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2025/10/4
Y1 - 2025/10/4
N2 - 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.
AB - 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.
KW - Subgraph Gaussian embeddings
KW - graph representation learning
KW - optimal transport
KW - self-supervised learning
UR - https://www.scopus.com/pages/publications/105020014949
U2 - 10.1007/978-3-032-06106-5_25
DO - 10.1007/978-3-032-06106-5_25
M3 - Conference contribution
AN - SCOPUS:105020014949
SN - 9783032061058
T3 - Lecture Notes in Computer Science
SP - 430
EP - 447
BT - Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2025, Proceedings
A2 - Ribeiro, Rita P.
A2 - Soares, Carlos
A2 - Gama, João
A2 - Pfahringer, Bernhard
A2 - Japkowicz, Nathalie
A2 - Larrañaga, Pedro
A2 - Jorge, Alípio M.
A2 - Abreu, Pedro H.
PB - Springer Science and Business Media Deutschland GmbH
T2 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2025
Y2 - 15 September 2025 through 19 September 2025
ER -