Teacher Retains Full Tokens, Student Merges Efficiently: TM20K for E-Commerce Sequence Modeling in Ad Recommendation

• URL: http://arxiv.org/abs/2608.07055v2
• Date: Thu, 13 Aug 2026 08:12:50 GMT
• Title: Teacher Retains Full Tokens, Student Merges Efficiently: TM20K for E-Commerce Sequence Modeling in Ad Recommendation
• Abstract summary: In this paper, we balance the effectiveness and efficiency for ultra-long sequence modeling via transformer modeling.<n>For student models, we propose several simple yet well-motivated token merge approaches, significantly compressing the sequence length.<n>Then, a one-time teacher is heavily trained with full sequence tokens, further boosting the performance of student models.<n>The proposed paradigm named TM20K has been successfully deployed in ByteDance's e-commerce advertising recommender system.
• Score: 19.958475935304175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Benefiting from ultra-long behavior sequence modeling, existing recommender systems bring users a better experience via simultaneously considering their long-term and short-term interests. Nevertheless, extended sequence lengths introduce substantial burdens on training efficiency and serving throughput. Prior approaches typically utilize search-based or cluster-based compression on ultra-long sequences at the cost of fine-grained information, or rely on various lightweight target attention structures incapable of sufficient sequential feature extraction. In this paper, we balance the effectiveness and efficiency for ultra-long sequence modeling via full transformer modeling accompanied with a two-stage knowledge distillation framework. First, both teacher and student models take the full attention mechanism rather than pure target-sequence attention for effective sequence scaling. For student models, we propose several simple yet well-motivated token merge approaches, significantly compressing the sequence length while maintaining an acceptable performance. Then, a one-time teacher is heavily trained with full sequence tokens, further boosting the performance of student models via knowledge distillation. The proposed paradigm named TM20K has been successfully deployed in ByteDance's e-commerce advertising recommender system that extends the e-commerce sequence length to 20K, delivering substantial improvements in key business metrics (e.g., ADSS +1.036\%) while keeping the training and serving cost nearly the same as the online state-of-the-art model (e.g., serving latency only +5.6\%).

Related papers

• SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching [17.335538522124555]
  SequenceO1 is an end-to-end framework for ultra-long user behavior sequence modeling.<n>It is deployed at full traffic on Douyin with histories of up to 100K interactions.<n>Results show consistent offline and online gains, while sketch retains most of the benefit of directly scaling end-to-end sequence ranking to 100K.
  arXiv  Detail & Related papers  (2026-09-08T08:49:44Z)
• Intra-class Patch Swap for Self-Distillation [3.282914142012984]
  We propose a teacher-free distillation framework based on a single student network.<n>Our approach is built on a simple yet highly effective augmentation, called intra-class patch swap augmentation.<n>Our method consistently outperforms both existing self-distillation baselines and conventional teacher-based KD approaches.
  arXiv  Detail & Related papers  (2025-05-20T09:30:19Z)
• LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders [23.70714095931094]
  Long-sequence optimized traNsformer for GPU-Efficient Recommenders.<n>Longer consistently outperforms strong baselines in offline metrics and online A/B testing.
  arXiv  Detail & Related papers  (2025-05-07T13:54:26Z)
• Active Data Curation Effectively Distills Large-Scale Multimodal Models [66.23057263509027]
  Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones.<n>In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining.<n>Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations.
  arXiv  Detail & Related papers  (2024-11-27T18:50:15Z)
• Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation [69.60321475454843]
  We propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. In the pre-training stage, we propose a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module.
  arXiv  Detail & Related papers  (2024-08-21T06:48:38Z)
• Efficient User Sequence Learning for Online Services via Compressed Graph Neural Networks [18.068737439570402]
  Graph Neural Networks (GNNs) have been extensively applied to model sequence relationships, and extract information from similar sequences. We propose a novel unified framework called ECSeq, to introduce graph compression techniques into relation modeling for user sequence representation learning.
  arXiv  Detail & Related papers  (2024-06-05T06:22:11Z)
• Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping [53.454408491386886]
  bootstrapping self-alignment markedly surpasses the single-round approach. We propose Step-On-Feet Tuning (SOFT) which leverages model's continuously enhanced few-shot ability to boost zero or one-shot performance. Based on easy-to-hard training recipe, we propose SOFT+ which further boost self-alignment's performance.
  arXiv  Detail & Related papers  (2024-02-12T12:30:42Z)
• Revisiting the Power of Prompt for Visual Tuning [50.11465784194896]
  This study explores the correlation evolvement between prompts and patch tokens during proficient training. Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes. Our method significantly advances the adaptation for self-supervised pretraining, achieving impressive task performance gains of at least 10% to 30%.
  arXiv  Detail & Related papers  (2024-02-04T07:49:02Z)
• TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer [34.790081960470964]
  We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) We make advanced modifications that include positional embedding, linear attention acceleration, gating mechanisms, tensor normalization, and inference acceleration and stabilization. We validate our model design through a series of ablations and train models with sizes of 385M, 1B, and 7B on our self-collected corpus.
  arXiv  Detail & Related papers  (2023-07-27T16:45:33Z)
• AttentionLite: Towards Efficient Self-Attention Models for Vision [9.957033392865982]
  We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. We can simultaneously distill knowledge from a compute-heavy teacher while also pruning the student model in a single pass of training.
  arXiv  Detail & Related papers  (2020-12-21T17:54:09Z)
• Efficient Crowd Counting via Structured Knowledge Transfer [122.30417437707759]
  Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. We propose a novel Structured Knowledge Transfer framework to generate a lightweight but still highly effective student network. Our models obtain at least 6.5$times$ speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-23T08:05:41Z)
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers [117.67424061746247]
  We present a simple and effective approach to compress large Transformer based pre-trained models. We propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Experimental results demonstrate that our monolingual model outperforms state-of-the-art baselines in different parameter size of student models.
  arXiv  Detail & Related papers  (2020-02-25T15:21:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.