作者位次 #4/4SIGIR 2026Oral· Information Retrieval (Full)
Adaptive Rich-kernelized Contrastive Learning for Capacity Enhancement in Collaborative Filtering
Jie Yang · Ling Luo · Nestor Cabello · Lars Kulik
摘要
Recent research has shown that single-vector embedding retrieval models face a fundamental bottleneck: the finite dimensionality of single-vector representations limits their capacity to represent arbitrary top-k relevant item combinations, even with perfect training. This inherent bottleneck sub...