Tag
This paper proposes SCISE, a scalable unsupervised graph clustering framework that uses community-aware sampling and structural entropy to overcome structural isolation in mini-batch training, achieving state-of-the-art results on benchmark datasets.
This paper derives batch scaling laws for sketched linear regression under power-law spectra, analyzing one-pass and multi-pass mini-batch SGD. It provides explicit risk decompositions showing how batch size affects bias, variance, and fluctuation terms, and establishes that without-replacement sampling yields lower noise than with-replacement.