Pith. sign in

REVIEW 11 cited by

Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.03900 v2 pith:JPBFNJUM submitted 2024-03-06 cs.IR

Chengkai Liu , Jianghao Lin , Jianling Wang , Hanzhou Liu , James Caverlee This is my paper · ORCID
classification cs.IR
keywords sequentialmamba4recrecommendationefficientmodelsselectiveefficiencyinference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Sequential recommendation aims to estimate the dynamic user preferences and sequential dependencies among historical user behaviors. Although Transformer-based models have proven to be effective for sequential recommendation, they suffer from the inference inefficiency problem stemming from the quadratic computational complexity of attention operators, especially for long behavior sequences. Inspired by the recent success of state space models (SSMs), we propose Mamba4Rec, which is the first work to explore the potential of selective SSMs for efficient sequential recommendation. Built upon the basic Mamba block which is a selective SSM with an efficient hardware-aware parallel algorithm, we design a series of sequential modeling techniques to further promote model performance while maintaining inference efficiency. Through experiments on public datasets, we demonstrate how Mamba4Rec effectively tackles the effectiveness-efficiency dilemma, outperforming both RNN- and attention-based baselines in terms of both effectiveness and efficiency. The code is available at https://github.com/chengkai-liu/Mamba4Rec.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GRAIN: Molecules Are Not the Right Granularity -- Active-Ingredient Modeling for Safe Medication Recommendation

    q-bio.QM 2026-07 conditional novelty 6.0 of 10

    Ingredient-level DDI modeling with a Mamba backbone improves MIMIC-IV medication recommendation accuracy while cutting the drug-level DDI rate in a matched comparison.

  2. Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

    cs.IR 2026-07 conditional novelty 6.0 of 10

    DeltaGate, a frozen-backbone plugin, routes each representation dimension between a user's pre-gap history and a learned global prior based on the inactivity gap, recovering part of the >365-day Hit@10 loss with 66K p...

  3. HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

    cs.IR 2026-02 conditional novelty 6.0 of 10

    Hierarchical semantic tokenization with sparse interest-agent voting and soft-routing attention compresses ultra-long user histories for recommenders, reporting a 1.65% online CTR lift at Taobao.

  4. Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model

    cs.IR 2025-05 conditional novelty 6.0 of 10

    HiT-LBM chunks lifelong user behavior, uses process-rating-guided tree search to select interest summaries, and fuses them temporally to improve recommendation performance.

  5. Flow Matching for Collaborative Filtering

    cs.IR 2025-02 conditional novelty 6.0 of 10

    FlowCF applies flow matching with a behavior-guided prior and a discrete flow framework to collaborative filtering, achieving state-of-the-art top-N recommendation accuracy with two-step inference.

  6. EvoReason: Self-Evolving Reasoning Primitive-Guided On-Policy Distillation for Latent Reasoning in Generative Recommendation

    cs.IR 2026-07 conditional novelty 5.0 of 10

    A self-evolving, primitive-guided distillation method for latent reasoning in generative recommendation reports consistent ranking gains over existing latent-reasoning baselines.

  7. Efficient Large-Scale Cross-Domain Sequential Recommendation with Dynamic State Representations

    cs.IR 2025-08 reject novelty 5.0 of 10

    For cross-domain sequential recommendation, restricting transformer attention to intra-domain items plus TAPE and DDSR cross-domain state mechanisms improves retrieval on Amazon 5-domain data over HSTU baselines.

  8. MambaRate: Speech Quality Assessment Across Different Sampling Rates

    cs.SD 2025-07 conditional novelty 5.0 of 10

    A compact Mamba-based predictor using frozen speech embeddings and radial-basis score encoding achieves strong MOS prediction with limited dependence on the audio sampling rate.

  9. Towards Transfer-Efficient Multi-modal Sequential Recommendation with State Space Duality

    cs.IR 2025-06 conditional novelty 5.0 of 10

    MMM4Rec uses a time-aware state space model with shared cross-modal projections and Fourier-filtered fusion to make multi-modal sequential recommenders transfer faster and more accurately.

  10. FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation

    cs.IR 2025-07 conditional novelty 4.0 of 10

    FindRec combines Mamba temporal encoding, RBF-kernel cross-modal alignment, and expert routing to improve multimodal sequential recommendation, reporting 1.0 to 3.3 percent relative gains over baselines, with no proof...

  11. Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation

    cs.CL 2025-05 unverdicted novelty 2.0 of 10

    A survey of small language models that organizes known methods into taxonomies but adds no new models, data, or validated benchmarks.

Pith tools