FastLane让检索模型更快更省，轻松对接大规模搜索系统。
FastLane: Efficient Routed Systems for Late-Interaction Retrieval
- 动态路由查询到最相关表示，避免无效计算
- 计算量降低30倍，精度仍保持领先
- 适合需要低延迟的搜索与推荐系统
像ColBERT这样的后期交互检索模型通过实现词级别交互获得更高准确率，但其计算开销限制了可扩展性及与近似最近邻搜索（ANNS）的集成。我们提出FastLane，一种新型检索框架，通过动态将查询路由至最具信息量的表示，消除冗余的词元比较。FastLane采用可学习的路由机制，与嵌入模型联合优化，利用自注意力和可微选择最大化效率。该方法将计算复杂度降低高达30倍，同时保持具有竞争力的检索性能。通过连接后期交互模型与ANNS，FastLane实现了可扩展、低延迟的检索，使搜索引擎、推荐系统和问答平台等大规模应用成为可能。本工作为多语言、多模态和长上下文检索开辟了新路径，推动高效自适应信息检索的发展。
原文摘要 · Abstract (English)
Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce FastLane, a novel retrieval framework that dynamically routes queries to their most informative representations, eliminating redundant token comparisons. FastLane employs a learnable routing mechanism optimized alongside the embedding model, leveraging self-attention and differentiable selection to maximize efficiency. Our approach reduces computational complexity by up to 30x while maintaining competitive retrieval performance. By bridging late-interaction models with ANNS, FastLane enables scalable, low-latency retrieval, making it feasible for large-scale applications such as search engines, recommendation systems, and question-answering platforms. This work opens pathways for multi-lingual, multi-modal, and long-context retrieval, pushing the frontier of efficient and adaptive information retrieval.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。