Scalable Sequential Recommendation under Latency and Memory Constraints

TL;DR

HoloMambaRec is a lightweight, scalable sequential recommendation model that efficiently incorporates metadata using holographic representations and a shallow encoder, outperforming traditional models under strict latency and memory constraints.

Contribution

The paper introduces HoloMambaRec, a novel architecture combining holographic embeddings with a shallow state space encoder for efficient, metadata-aware sequential recommendation.

Findings

Outperforms SASRec on Amazon Beauty and MovieLens-1M datasets.

Achieves state-of-the-art ranking on MovieLens-1M.

Maintains lower memory complexity than transformer-based models.

Abstract

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.