Group Contrastive Self-Supervised Learning on Graphs
- URL: http://arxiv.org/abs/2107.09787v1
- Date: Tue, 20 Jul 2021 22:09:21 GMT
- Title: Group Contrastive Self-Supervised Learning on Graphs
- Authors: Xinyi Xu, Cheng Deng, Yaochen Xie, Shuiwang Ji
- Abstract summary: We study self-supervised learning on graphs using contrastive methods.
We argue that contrasting graphs in multiple subspaces enables graph encoders to capture more abundant characteristics.
- Score: 101.45974132613293
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study self-supervised learning on graphs using contrastive methods. A
general scheme of prior methods is to optimize two-view representations of
input graphs. In many studies, a single graph-level representation is computed
as one of the contrastive objectives, capturing limited characteristics of
graphs. We argue that contrasting graphs in multiple subspaces enables graph
encoders to capture more abundant characteristics. To this end, we propose a
group contrastive learning framework in this work. Our framework embeds the
given graph into multiple subspaces, of which each representation is prompted
to encode specific characteristics of graphs. To learn diverse and informative
representations, we develop principled objectives that enable us to capture the
relations among both intra-space and inter-space representations in groups.
Under the proposed framework, we further develop an attention-based representor
function to compute representations that capture different substructures of a
given graph. Built upon our framework, we extend two current methods into
GroupCL and GroupIG, equipped with the proposed objective. Comprehensive
experimental results show our framework achieves a promising boost in
performance on a variety of datasets. In addition, our qualitative results show
that features generated from our representor successfully capture various
specific characteristics of graphs.
Related papers
- Entropy Neural Estimation for Graph Contrastive Learning [9.032721248598088]
Contrastive learning on graphs aims at extracting distinguishable high-level representations of nodes.
We propose a simple yet effective subset sampling strategy to contrast pairwise representations between views of a dataset.
We conduct extensive experiments on seven graph benchmarks, and the proposed approach achieves competitive performance.
arXiv Detail & Related papers (2023-07-26T03:55:08Z) - Semantic Random Walk for Graph Representation Learning in Attributed
Graphs [2.318473106845779]
We propose a novel semantic graph representation (SGR) method to formulate the joint optimization of the two heterogeneous sources into a common high-order proximity based framework.
Conventional embedding methods that consider high-order topology proximities can then be easily applied to the newly constructed graph to learn the representations of both node and attribute.
The learned attribute embeddings can also effectively support some semantic-oriented inference tasks, helping to reveal the graph's deep semantic.
arXiv Detail & Related papers (2023-05-11T02:35:16Z) - Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
Contrastive learning has emerged as a premier method for learning representations with or without supervision.
Recent studies have shown its utility in graph representation learning for pre-training.
We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
arXiv Detail & Related papers (2023-02-06T16:26:29Z) - CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph
Similarity Learning [65.1042892570989]
We propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning.
We employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning.
We transform node representations into graph-level representations via pooling operations for graph similarity computation.
arXiv Detail & Related papers (2022-05-30T13:20:26Z) - GraphCoCo: Graph Complementary Contrastive Learning [65.89743197355722]
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
This paper proposes an effective graph complementary contrastive learning approach named GraphCoCo to tackle the above issue.
arXiv Detail & Related papers (2022-03-24T02:58:36Z) - InfoGCL: Information-Aware Graph Contrastive Learning [26.683911257080304]
We study how graph information is transformed and transferred during the contrastive learning process.
We propose an information-aware graph contrastive learning framework called InfoGCL.
We show for the first time that all recent graph contrastive learning methods can be unified by our framework.
arXiv Detail & Related papers (2021-10-28T21:10:39Z) - Effective and Efficient Graph Learning for Multi-view Clustering [173.8313827799077]
We propose an effective and efficient graph learning model for multi-view clustering.
Our method exploits the view-similar between graphs of different views by the minimization of tensor Schatten p-norm.
Our proposed algorithm is time-economical and obtains the stable results and scales well with the data size.
arXiv Detail & Related papers (2021-08-15T13:14:28Z) - Multi-Level Graph Contrastive Learning [38.022118893733804]
We propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs.
The original graph is first-order approximation structure and contains uncertainty or error, while the $k$NN graph generated by encoding features preserves high-order proximity.
Extensive experiments indicate MLGCL achieves promising results compared with the existing state-of-the-art graph representation learning methods on seven datasets.
arXiv Detail & Related papers (2021-07-06T14:24:43Z) - A Robust and Generalized Framework for Adversarial Graph Embedding [73.37228022428663]
We propose a robust framework for adversarial graph embedding, named AGE.
AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution.
Based on this framework, we propose three models to handle three types of graph data.
arXiv Detail & Related papers (2021-05-22T07:05:48Z) - Graph Representation Learning by Ensemble Aggregating Subgraphs via
Mutual Information Maximization [5.419711903307341]
We introduce a self-supervised learning method to enhance the representations of graph-level learned by Graph Neural Networks.
To get a comprehensive understanding of the graph structure, we propose an ensemble-learning like subgraph method.
And to achieve efficient and effective contrasive learning, a Head-Tail contrastive samples construction method is proposed.
arXiv Detail & Related papers (2021-03-24T12:06:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.