TaLK distills TAG datasets via LM coupled with graph-aware NTK, outperforming baselines and reaching up to 97% full-dataset performance with 1% synthetic data.
arXiv preprint arXiv:2104.08448 , year=
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
-
TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel
TaLK distills TAG datasets via LM coupled with graph-aware NTK, outperforming baselines and reaching up to 97% full-dataset performance with 1% synthetic data.