Learning vectorized embeddings is at the core of various recommender systems for user-item matching. To perform efficient online inference, representation quantization, aiming to embed the latent features by a compact sequence of discrete numbers, recently shows the promising potentiality in optimizing both memory and computation overheads. However, existing work merely focuses on numerical quantization whilst ignoring the concomitant information loss issue, which, consequently, leads to conspicuous performance degradation. In this paper, we propose a novel quantization framework to learn Binarized Graph Representations for Top-K Recommendation (BiGeaR). BiGeaR introduces multi-faceted quantization reinforcement at the pre-, mid-, and post-stage of binarized representation learning, which substantially retains the representation informativeness against embedding binarization. In addition to saving the memory footprint, BiGeaR further develops solid online inference acceleration with bitwise operations, providing alternative flexibility for the realistic deployment. The empirical results over five large real-world benchmarks show that BiGeaR achieves about 22%~40% performance improvement over the state-of-the-art quantization-based recommender system, and recovers about 95%~102% of the performance capability of the best full-precision counterpart with over 8x time and space reduction.
翻译:学习矢量嵌入是各种用户项目匹配推荐系统的核心。 要高效进行在线推断, 代表量量化, 目的是通过离散数字的紧凑序列嵌入潜在特征, 最近显示在优化记忆和计算间接费用方面大有潜力。 然而, 现有工作仅侧重于量化, 忽视随之而来的信息丢失问题, 从而导致明显性能退化。 在本文件中, 我们提议了一个创新的量化框架, 以学习高K建议( BiGeaR) 的“ 批量图形表示 ” ( BiGeaR) 。 BiGeaR 在二进制演示学习的预、 中和后阶段引入了多面量化增强功能, 从而大大保留了与嵌入二进制相关的信息性能。 除了保存记忆足迹外, BiGeaR 进一步开发了可靠的在线推导加速, 为现实部署提供了其他灵活性。 超过五个大现实世界基准的实证结果表明, BiGeaR 在州- 40% 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州- 州