Diagnoses attention dispersion in CTDG Transformers under temporal shift and introduces differential attention to suppress common signals and achieve SOTA on shifted benchmarks.
Title resolution pending
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
-
Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
Diagnoses attention dispersion in CTDG Transformers under temporal shift and introduces differential attention to suppress common signals and achieve SOTA on shifted benchmarks.