PACE: Progressive Angular-to-Norm Contrastive Embedding
This paper proposes PACE, a two-stage framework that progressively expands both the representation and trainable parameter spaces, and introduces Focal Embedding Loss, a confidence-adaptive objective that downweights queries with high positive retrieval confidence while emphasizing ambiguous queries with competitive ne...
Yan-Ping Li, Wei Zhou, Ya-Wen Liu et al.
· 1 citation