SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift
Generative models trained on a source domain often produce samples that are poorly aligned with shifted target domains, limiting their effectiveness for target-domain data augmentation. Although target-specific adaptation can reduce this mismatch, it typically requires additional optimization and domain-specific parameters. We propose a Similarity-based Generative Network (SGN), a reusable framework that is trained once on labeled source data and applied to new target domains without parameter updates. SGN learns a latent space structured by label-induced pairwise similarities while preserving
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “SGN: A Similarity-based Generative Network for Data Generati” ≈ “GoogleCloudPlatform/generative-ai””
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: luo”
- LinkedLinked via arxiv author · 85%Jiaqi Zhu →
“SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift”
- LinkedLinked via arxiv author · 85%Xincheng Chen →
“SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift”
- LinkedLinked via arxiv author · 85%Yuncheng Wu →
“SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift”
- LinkedLinked via arxiv author · 85%Zhaojing Luo →
“SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift”
- LinkedLinked via arxiv author · 85%Beng Chin Ooi →
“SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift”