MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Qihang, Fu, Kairui, Du, Zhaocheng, Si, Yuxuan, Li, Kaiyuan, Zhao, Weihao, Zhang, Zhicheng, Zhu, Jieming, Dai, Quanyu, Dong, Zhenhua, Zhang, Shengyu, Kuang, Kun, Wu, Fei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915760384770048
author Yu, Qihang
Fu, Kairui
Du, Zhaocheng
Si, Yuxuan
Li, Kaiyuan
Zhao, Weihao
Zhang, Zhicheng
Zhu, Jieming
Dai, Quanyu
Dong, Zhenhua
Zhang, Shengyu
Kuang, Kun
Wu, Fei
author_facet Yu, Qihang
Fu, Kairui
Du, Zhaocheng
Si, Yuxuan
Li, Kaiyuan
Zhao, Weihao
Zhang, Zhicheng
Zhu, Jieming
Dai, Quanyu
Dong, Zhenhua
Zhang, Shengyu
Kuang, Kun
Wu, Fei
contents The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both industry and academia. However, the advent of large-scale recommenders also brings significantly higher computational costs, particularly under the long-sequence dependencies inherent in the user intent of recommendation systems. Current approaches often rely on pre-storing the intermediate states of the past behavior for each user, thereby reducing the quadratic re-computation cost for the following requests. Despite their effectiveness, these methods often treat memory merely as a medium for acceleration, without adequately considering the space overhead it introduces. This presents a critical challenge in real-world recommendation systems with billions of users, each of whom might initiate thousands of interactions and require massive memory for state storage. Fortunately, there have been several memory management strategies examined for compression in LLM, while most have not been evaluated on the recommendation task. To mitigate this gap, we introduce MALLOC, a comprehensive benchmark for memory-aware long sequence compression. MALLOC presents a comprehensive investigation and systematic classification of memory management techniques applicable to large sequential recommendations. These techniques are integrated into state-of-the-art recommenders, enabling a reproducible and accessible evaluation platform. Through extensive experiments across accuracy, efficiency, and complexity, we demonstrate the holistic reliability of MALLOC in advancing large-scale recommendation. Code is available at https://anonymous.4open.science/r/MALLOC.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20234
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation
Yu, Qihang
Fu, Kairui
Du, Zhaocheng
Si, Yuxuan
Li, Kaiyuan
Zhao, Weihao
Zhang, Zhicheng
Zhu, Jieming
Dai, Quanyu
Dong, Zhenhua
Zhang, Shengyu
Kuang, Kun
Wu, Fei
Information Retrieval
Artificial Intelligence
The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both industry and academia. However, the advent of large-scale recommenders also brings significantly higher computational costs, particularly under the long-sequence dependencies inherent in the user intent of recommendation systems. Current approaches often rely on pre-storing the intermediate states of the past behavior for each user, thereby reducing the quadratic re-computation cost for the following requests. Despite their effectiveness, these methods often treat memory merely as a medium for acceleration, without adequately considering the space overhead it introduces. This presents a critical challenge in real-world recommendation systems with billions of users, each of whom might initiate thousands of interactions and require massive memory for state storage. Fortunately, there have been several memory management strategies examined for compression in LLM, while most have not been evaluated on the recommendation task. To mitigate this gap, we introduce MALLOC, a comprehensive benchmark for memory-aware long sequence compression. MALLOC presents a comprehensive investigation and systematic classification of memory management techniques applicable to large sequential recommendations. These techniques are integrated into state-of-the-art recommenders, enabling a reproducible and accessible evaluation platform. Through extensive experiments across accuracy, efficiency, and complexity, we demonstrate the holistic reliability of MALLOC in advancing large-scale recommendation. Code is available at https://anonymous.4open.science/r/MALLOC.
title MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2601.20234