Problem
Research questions and friction points this paper is trying to address.
visual document retrieval
multi-vector page embeddings
index storage overhead
MaxSim scoring overhead
post-hoc merging
MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval
🤖 AI Summary
本文提出MAGIC方法，通过最优传输解决视觉文档检索中多向量页嵌入导致的存储和评分开销问题，提高检索效率。
📝 Abstract
Recent visual document retrieval (VDR) systems such as ColPali use multi-vector page embeddings, in which patch-level vectors enable fine-grained evidence matching but incur substantial index storage and MaxSim scoring overhead. Post-hoc merging offers a practical route to efficient VDR by reducing this cost without retraining the retriever, but its uniform reconstruction objectives are poorly aligned with the sparse, non-uniform patch usage induced by late-interaction retrieval. Under aggressive compression, this misalignment can preserve rarely used patches while concentrating retrieval activity on too few retained representatives. To address this misalignment, we propose Marginal-Guided Compression with Optimal Transport (MAGIC), a training-free post-hoc compressor for efficient retrieval with frozen multi-vector embeddings. MAGIC derives a MaxSim-induced compression surrogate and optimizes it through a two-marginal entropic optimal-transport formulation, where a retrieval-demand source marginal prioritizes high-use patches and a balanced target marginal regularizes retained-facet usage. Across ViDoRe benchmarks, keep ratios, and retrieval backbones, MAGIC consistently outperforms strong post-hoc compressors, with particularly large gains in the aggressive-compression regime; component ablations verify the complementary effects of its two marginals. We release the code at: https://github.com/xandery-geek/MAGIC.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Optimal Transport
Efficient Retrieval
Multi-vector Embeddings
Post-hoc Compression
🔎 Similar Papers
No similar papers found.
