Pith. sign in

REVIEW 27 cited by

Self-Attentive Sequential Recommendation

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 1808.09781 v1 pith:2DBBRGE3 submitted 2018-08-20 cs.IR cs.LG

Wang-Cheng Kang , Julian McAuley This is my paper · ORCID
classification cs.IRcs.LG
keywords modeldatasetssequentialactionscapturernnsactionapproaches
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user's next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is critical, while RNNs perform better in denser datasets where higher model complexity is affordable. The goal of our work is to balance these two goals, by proposing a self-attention based sequential model (SASRec) that allows us to capture long-term semantics (like an RNN), but, using an attention mechanism, makes its predictions based on relatively few actions (like an MC). At each time step, SASRec seeks to identify which items are `relevant' from a user's action history, and use them to predict the next item. Extensive empirical studies show that our method outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets. Moreover, the model is an order of magnitude more efficient than comparable CNN/RNN-based models. Visualizations on attention weights also show how our model adaptively handles datasets with various density, and uncovers meaningful patterns in activity sequences.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 27 Pith papers

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

  1. A Self-Attentive model for Knowledge Tracing

    cs.LG 2019-07 unverdicted novelty 7.0 of 10

    SAKT uses self-attention to focus on relevant prior KCs for performance prediction and reports 4.43% average AUC improvement over DKT and DKVMN on real datasets.

  2. HCGRec: Hint-Conditioned Generative Recommendation with Semantic IDs

    cs.IR 2026-08 conditional novelty 6.0 of 10

    HCGRec supplies the shortest target-prefix hint for hard training instances during GRPO post-training, then optimizes only the unhinted suffix, reducing zero-advantage rollout groups and improving sequential recommend...

  3. GenRec: An LLM-Backed Recommendation Ranker at Netflix

    cs.IR 2026-08 conditional novelty 6.0 of 10

    An LLM-backed ranker that scores the full Netflix catalog in a single prefill pass beats a mature production ranker on both offline MRR and live A/B metrics while using roughly 40x fewer Phase-2 labels.

  4. Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation

    cs.IR 2026-08 conditional novelty 6.0 of 10

    Per-sequence modality masking during training makes multi-modal sequential recommenders retain 1.0 to 3.2x more accuracy when text or images are missing at serving time.

  5. GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation

    cs.IR 2026-08 conditional novelty 6.0 of 10

    GARDRec improves LLM-based next-item ranking by grounding decisions in knowledge-graph embeddings, personalized graph contexts, and late-stage scoring rather than prompt text.

  6. Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    SIDs preserve coarse item organization but lose fine structure and prune good targets during generation; Item-Supported Decoding recovers up to 31.2% NDCG@10 without retraining.

  7. Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Prediction

    cs.AI 2026-07 conditional novelty 6.0 of 10

    SemRaD improves cold-start LTV and CVR prediction by encoding LLM-written semantic profiles with a learned gate and distilling a hindsight-reconciled future target through per-user distillation experts, confirmed by a...

  8. LLM-Based User Personas for Recommendations at Scale

    cs.IR 2026-06 unverdicted novelty 6.0 of 10

    A framework for real-time LLM-based user interest personas in large-scale video recommendations, using distillation, async inference, and video clustering to balance interests with novel topics and improve viewer valu...

  9. Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

    cs.LG 2026-02 conditional novelty 6.0 of 10

    LLM agents acting as ML engineers autonomously generated optimizer, architecture, and reward changes that produced small live metric gains at YouTube when deployed through a dual offline/online loop.

  10. Towards Comprehensible Recommendation with Large Language Model Fine-tuning

    cs.IR 2025-08 conditional novelty 6.0 of 10

    CURec aligns an LLM with recommendation objectives via RL, generates personalized user patterns and item-reason texts, and corrects them through a chronological loop, improving top-K recall and NDCG on MovieLens and Amazon.

  11. Not Just What, But When: Integrating Irregular Intervals to LLM for Sequential Recommendation

    cs.IR 2025-07 conditional novelty 6.0 of 10

    IntervalLLM integrates irregular time intervals into an LLM recommender via interval embeddings and interval-infused attention, improving next-item Hit Rate@1 on three benchmarks and adding a new interval-perspective ...

  12. DV365: Extremely Long User History Modeling at Instagram

    cs.IR 2025-05 conditional novelty 6.0 of 10

    A single offline foundation model encodes up to 70k user interactions into a compact embedding that lifts recommendation quality on top of strong production baselines.

  13. Temporal Collaborative Ranking Via Personalized Transformer

    cs.LG 2019-08 conditional novelty 6.0 of 10

    Adding SSE-regularized user embeddings to the SASRec transformer improves next-item ranking accuracy on benchmark datasets, and a long-sequence variant preserves most of the gain at lower cost.

  14. Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation

    cs.IR 2026-08 conditional novelty 5.0 of 10

    Adding cosine-similarity and contrastive structure-preserving losses to the projection step makes LLM-based sequential recommenders use collaborative signals and improves Hit Ratio at 1 on LastFM and MovieLens.

  15. From Bootstrapping to Sequence Modeling: A Unified Generative Framework for Personalized Landing-Page Modeling

    cs.IR 2026-06 unverdicted novelty 5.0 of 10

    GLAN replaces CQL bootstrapping with Decision Transformer sequence modeling for PLPM, using global inter-day (L-RTG) and local session (HRM) modules to achieve +0.158% DAU and +0.108% LT gains in Kuaishou online tests.

  16. DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    DUET pre-trains dedicated transformers for click and conversion streams, yielding up to 0.38% NE reduction over baselines in OCVR prediction.

  17. VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders

    cs.IR 2026-06 unverdicted novelty 5.0 of 10

    VirtualMLE deploys an LLM agent with execution-reflection-memory to tune sequential recommenders, reaching competitive quality on Amazon benchmarks with fewer trials and transferring heuristics across datasets.

  18. Representation Quantization for Collaborative Filtering Augmentation

    cs.IR 2025-08 conditional novelty 5.0 of 10

    DQRec uses an SVD-based vector quantizer to turn user and item embeddings into semantic IDs, then augments collaborative filtering with these IDs as features and as similar-neighbor links.

  19. A Contextual-Aware Position Encoding for Sequential Recommendation

    cs.IR 2025-02 conditional novelty 5.0 of 10

    CAPE computes context-dependent positions from item dissimilarity and fuses them into attention, improving sequential recommenders on benchmark and live-traffic tests.

  20. Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models

    cs.IR 2024-12 conditional novelty 5.0 of 10

    RSLLM mixes item ID embeddings from classical recommenders with text titles inside an LLM prompt and uses two-stage contrastive fine-tuning to improve sequential recommendation.

  21. An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking

    cs.IR 2026-02 conditional novelty 4.0 of 10

    A transformer-based sequential recommender, Feed SR, improved LinkedIn Feed time spent by 2.10% in an online A/B test and now serves the majority of Feed traffic.

  22. Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation

    cs.IR 2026-02 conditional novelty 4.0 of 10

    GLASS extends generative retrieval with a tiered long-term interest vector and a first-SID-keyed search of long histories, reporting consistent gains over Tiger and DualGR on two public datasets.

  23. A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation

    cs.IR 2025-06 conditional novelty 4.0 of 10

    With a common EasyRec implementation, BSARec consistently beats SASRec on MovieLens-1M and Foursquare-NYC, but the gains are smaller than the original BSARec paper reported.

  24. Style4Rec: Enhancing Transformer-based E-commerce Recommendation Systems with Style and Shopping Cart Information

    cs.IR 2025-01 reject novelty 4.0 of 10

    Adding VGG-19 style embeddings and shopping cart training sessions to a transformer recommender raised HR@5 from 0.681 to 0.735 on a proprietary e-commerce dataset.

  25. e-Fold Cross-Validation for Recommender-System Evaluation

    cs.LG 2024-12 conditional novelty 4.0 of 10

    A simulation finds that e-fold cross-validation, which stops folding when the confidence interval of the mean stabilizes, uses 41.5% of the energy of 10-fold cross-validation with an average 1.81% difference in results.

  26. Agentic Web: Weaving the Next Web with AI Agents

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A position paper defines the Agentic Web as the next web era and proposes a three-dimensional conceptual framework for understanding and building it.

  27. When Transformers Meet Recommenders: Integrating Self-Attentive Sequential Recommendation with Fine-Tuned LLMs

    cs.IR 2025-07 reject novelty 3.0 of 10

    SASRecLLM, a hybrid of SASRec and a LoRA-fine-tuned LLM, reports modest gains over TALLRec on MovieLens but shows inconsistent and contradictory results on Amazon and in warm-start settings.

Pith tools