DP-GCL improves differentially private contrastive learning by bounding group-level contributions through batch partitioning and intra-group augmentation, delivering 5.6% higher image classification accuracy and 20.1% higher retrieval accuracy than existing approaches.
Kingma and Jimmy Ba
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
TIDE disentangles habitual repurchase from exploratory interest in next-basket recommendation using Hawkes-enhanced Fourier time encoding, dual experts, and item-aware gating, outperforming prior methods on four datasets.
citing papers explorer
-
Differentially Private Contrastive Learning via Bounding Group-level Contribution
DP-GCL improves differentially private contrastive learning by bounding group-level contributions through batch partitioning and intra-group augmentation, delivering 5.6% higher image classification accuracy and 20.1% higher retrieval accuracy than existing approaches.
-
Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation
TIDE disentangles habitual repurchase from exploratory interest in next-basket recommendation using Hawkes-enhanced Fourier time encoding, dual experts, and item-aware gating, outperforming prior methods on four datasets.