Saved in:
Bibliographic Details
Main Authors: Parthasarathy, Adithya, Kirubakaran, Aswathnarayan Muthukrishnan, Punniyamoorthy, Vinoth, Chockalingam, Nachiappan, Butra, Lokesh, Kannan, Kabilan, Mazumder, Abhirup, Saha, Sumit
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08360
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912857029869568
author Parthasarathy, Adithya
Kirubakaran, Aswathnarayan Muthukrishnan
Punniyamoorthy, Vinoth
Chockalingam, Nachiappan
Butra, Lokesh
Kannan, Kabilan
Mazumder, Abhirup
Saha, Sumit
author_facet Parthasarathy, Adithya
Kirubakaran, Aswathnarayan Muthukrishnan
Punniyamoorthy, Vinoth
Chockalingam, Nachiappan
Butra, Lokesh
Kannan, Kabilan
Mazumder, Abhirup
Saha, Sumit
contents Sequential recommender systems must model long-range user behavior while operating under strict memory and latency constraints. Transformer-based approaches achieve strong accuracy but suffer from quadratic attention complexity, forcing aggressive truncation of user histories and limiting their practicality for long-horizon modeling. This paper presents HoloMambaRec, a lightweight sequential recommendation architecture that combines holographic reduced representations for attribute-aware embedding with a selective state space encoder for linear-time sequence processing. Item and attribute information are bound using circular convolution, preserving embedding dimensionality while encoding structured metadata. A shallow selective state space backbone, inspired by recent Mamba-style models, enables efficient training and constant-time recurrent inference. Experiments on Amazon Beauty and MovieLens-1M under a 10-epoch budget show that HoloMambaRec surpasses SASRec on both datasets, attains state-of-the-art ranking on MovieLens-1M, and trails only GRU4Rec on Amazon Beauty, all while maintaining substantially lower memory complexity. The design further incorporates forward-compatible mechanisms for temporal bundling and inference-time compression, positioning HoloMambaRec as a practical and extensible alternative for scalable, metadata-aware sequential recommendation.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08360
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scalable Sequential Recommendation under Latency and Memory Constraints
Parthasarathy, Adithya
Kirubakaran, Aswathnarayan Muthukrishnan
Punniyamoorthy, Vinoth
Chockalingam, Nachiappan
Butra, Lokesh
Kannan, Kabilan
Mazumder, Abhirup
Saha, Sumit
Information Retrieval
Artificial Intelligence
Sequential recommender systems must model long-range user behavior while operating under strict memory and latency constraints. Transformer-based approaches achieve strong accuracy but suffer from quadratic attention complexity, forcing aggressive truncation of user histories and limiting their practicality for long-horizon modeling. This paper presents HoloMambaRec, a lightweight sequential recommendation architecture that combines holographic reduced representations for attribute-aware embedding with a selective state space encoder for linear-time sequence processing. Item and attribute information are bound using circular convolution, preserving embedding dimensionality while encoding structured metadata. A shallow selective state space backbone, inspired by recent Mamba-style models, enables efficient training and constant-time recurrent inference. Experiments on Amazon Beauty and MovieLens-1M under a 10-epoch budget show that HoloMambaRec surpasses SASRec on both datasets, attains state-of-the-art ranking on MovieLens-1M, and trails only GRU4Rec on Amazon Beauty, all while maintaining substantially lower memory complexity. The design further incorporates forward-compatible mechanisms for temporal bundling and inference-time compression, positioning HoloMambaRec as a practical and extensible alternative for scalable, metadata-aware sequential recommendation.
title Scalable Sequential Recommendation under Latency and Memory Constraints
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2601.08360