BSG adds neighbor, minimal, and divergence losses to graph self-supervised learning, balancing embedding smoothness and improving downstream node and link tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
BSG adds neighbor, minimal, and divergence losses to graph self-supervised learning, balancing embedding smoothness and improving downstream node and link tasks.