通过结构重参数化加速推荐系统排序模型，零精度损失。
MaRI: Accelerating Ranking Model Inference via Structural Re-parameterization in Large Scale Recommendation System
- 重构特征融合矩阵乘法结构，消除用户侧冗余计算。
- 在真实推荐系统中实现推理加速，精度无损。
- 适合对延迟敏感且需保持高精度的在线推荐场景。
排序模型（包括粗排序与精排序模型）是大规模推荐系统的核心组件，负责根据用户偏好对海量候选物品进行打分。为满足线上服务的严格延迟要求，通常采用结构轻量化或知识蒸馏技术来加速排序模型。然而，这些方法往往导致显著的精度下降。值得注意的是，通过结构重参数化优化特征融合矩阵乘法以实现无损加速的角度尚未被充分探索。本文提出 MaRI，一种新型的矩阵重参数化推理框架，作为现有技术的补充，在不损失精度的前提下加速排序模型推理。MaRI 的动机源于观察到特征融合矩阵乘法中用户侧计算存在冗余，因此采用结构重参数化思想缓解该冗余问题。
原文摘要 · Abstract (English)
Ranking models, i.e., coarse-ranking and fine-ranking models, serve as core components in large-scale recommendation systems, responsible for scoring massive item candidates based on user preferences. To meet the stringent latency requirements of online serving, structural lightweighting or knowledge distillation techniques are commonly employed for ranking model acceleration. However, these approaches typically lead to a non-negligible drop in accuracy. Notably, the angle of lossless acceleration by optimizing feature fusion matrix multiplication, particularly through structural reparameterization, remains underexplored. In this paper, we propose MaRI, a novel Matrix Re-parameterized Inference framework, which serves as a complementary approach to existing techniques while accelerating ranking model inference without any accuracy loss. MaRI is motivated by the observation that user-side computation is redundant in feature fusion matrix multiplication, and we therefore adopt the philosophy of structural reparameterization to alleviate such redundancy.
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。