.png){kind=icon}
Return
Self-Supervised Graph Representation Learning via Topology Transformations
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2021.3133439.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present the Topology Transformation Equivariant Representation learning, a general paradigm of self-supervised learning for node representations of graph data to enable the wide applicability of Graph Convolutional Neural Networks (GCNNs). We formalize the proposed model from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations. We derive that maximizing such mutual information can be relaxed to minimizing the cross entropy between the applied topology transformation and its estimation from node representations. In particular, we seek to sample a subset of node pairs from the original graph and flip the edge connectivity between each pair to transform the graph topology. Then, we self-train a representation encoder to learn node representations by reconstructing the topology transformations from the feature representations of the original and transformed graphs. In experiments, we apply the proposed model to the downstream node classification, graph classification and link prediction tasks, and results show that the proposed method outperforms the state-of-the-art unsupervised approaches.
Keywords:
Topology
Representation learning
Network topology
Mutual information
Data models
Task analysis
Transforms
Self-supervised learning
graph representation learning
topology transformation
transformation equivariant representation
Journal
IF:
10.4
Papers:
6.9K
Citations:
3.2W
Organization
Cited Papers
More tricks with tetramers: a practical guide to staining T cells with peptide–MHC multimers.png)
Immunology
OAAI
ImmunologyIF0
OAAIShareSavePassive signal propagation and membrane properties in median photoreceptors of the giant barnacleOAAI
OAAIShareSaveShareSaveShareSave
View more