PromptDyG performs unsupervised test-time prompt adaptation on frozen dynamic graph models via entropy minimization to guarantee larger positive-negative pair margins and improve online predictions.
Moreover, Matcha can be combined with existing TTA methods to jointly handle structure and attribute shifts, achieving robust performance under diverse distribution shift settings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
PromptDyG performs unsupervised test-time prompt adaptation on frozen dynamic graph models via entropy minimization to guarantee larger positive-negative pair margins and improve online predictions.