Lune

WWW2020Top-tier venue

LightRec: A Memory and Search-Efficient Recommender System

Defu Lian, Haoyu Wang, Zheng Liu, Jianxun Lian, Enhong Chen, Xing Xie

Abstract

Deep recommender systems have achieved remarkable improvements in recent years. Despite its superior ranking precision, the running efficiency and memory consumption turn out to be severe bottlenecks in reality. To overcome both limitations, we propose LightRec, a lightweight recommender system which enjoys fast online inference and economic memory consumption. The backbone of LightRec is a total of B codebooks, each of which is composed of W latent vectors, known as codewords. On top of such a structure, LightRec will have an item represented as additive composition of B codewords, which are optimally selected from each of the codebooks. To effectively learn the codebooks from data, we devise an end-to-end learning workflow, where challenges on the inherent differentiability and diversity are conquered by the proposed techniques. In addition, to further improve the representation quality, several distillation strategies are employed, which better preserves user-item relevance scores and relative ranking orders. LightRec is extensively evaluated with four real-world datasets, which gives rise to two empirical findings: 1) compared with those the state-of-the-art lightweight baselines, LightRec achieves over 11% relative improvements in terms of recall performance; 2) compared to conventional recommendation algorithms, LightRec merely incurs negligible accuracy degradation while leads to more than 27x speedup in top-k recommendation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

26 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers26

  1. Learning Vector-Quantized Item Representation for Transferable Sequential RecommendersYupeng Hou, Zhankui He, Julian J. McAuley, Wayne Xin ZhaoWWW 2023 · 256 citations
  2. VBASE: Unifying Online Vector Similarity Search and Relational Queries via Relaxed MonotonicityQianxi Zhang, Shuotao Xu, Qi Chen, Guoxin Sui et al.OSDI 2023 · 75 citations
  3. Similarity search in the blink of an eye with compressed indicesCecilia Aguerrebere, Ishwar Singh Bhati, Mark Hildebrand, Mariano Tepper et al.VLDB 2023 · 64 citations
  4. Learning Elastic Embeddings for Customizing On-Device RecommendersTong Chen, Hongzhi Yin, Yujia Zheng, Zi Huang et al.KDD 2021 · 50 citations
  5. Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsShitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang et al.SIGIR 2022 · 31 citations

Related papers

  1. LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query InferenceGuangyuan Ma, Yongliang Ma, Xuanrui Gou, Zhenpeng Su et al.ICLR 2026 · 3 citations
  2. xLightFM: Extremely Memory-Efficient Factorization MachineGangwei Jiang, Hao Wang, Jin Chen, Haoyu Wang et al.SIGIR 2021 · 25 citations
  3. Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation SystemsHao-Jun Michael Shi, Dheevatsa Mudigere, Maxim Naumov, Jiyan YangKDD 2020 · 88 citations
  4. Decoding in Latent Spaces for Efficient Inference in LLM-based RecommendationChengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi et al.EMNLP Findings 2025 · 2 citations
  5. Hybrid Embedding Framework for Memory-Efficient Recommendation SystemsSeung Jin Yang, Hyuk-Jae Lee, Chae-Eun RheeDAC 2025
Dusk over the sea between two cliffs drawn in fine vertical lines