AI 中文总结
研究基于套娃表示学习扩展假设编码器，支持多种大小Q-Nets以权衡有效性和效率。该“套娃式假设编码器”在域内参数大幅减少，吞吐量提升，为假设编码器实际部署奠定基础。
AI 中文摘要
假设编码器是一种最近提出的检索方法，它将查询编码为浅层神经网络（“Q-Nets”），以估计预先计算的文档嵌入的相关性。受套娃表示学习的启发，我们表明假设编码器可以扩展以支持多种大小的Q-Nets，在部署时允许在有效性和效率之间进行权衡。我们发现这种“套娃式假设编码器”在域内实现了相当的有效性，域内活动参数减少约7倍，域外活动参数减少一半，这对应于评分吞吐量提高1.6 - 3.4倍。这项工作为假设编码器的实际部署铺平了道路。
英文摘要
The Hypencoder is a recently-proposed retrieval approach that encodes queries as shallow neural networks ("Q-Nets") that estimate relevance over pre-computed document embeddings. Inspired by Matryoshka Representation Learning, we show that the Hypencoder can be extended to support multiple sizes of Q-Nets, allowing trade-offs between effectiveness and efficiency when deployed. We find that this "Matryoshka Hypencoder" achieves comparable in-domain effectiveness with approximately 7x fewer active parameters in-domain and half as many active parameters out-of-domain, which corresponds to a 1.6-3.4x increase in scoring throughput. This work paves the way for practical deployment of Hypencoders.
CommentsSIGIR 2026
