Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models

• URL: http://arxiv.org/abs/2604.15650v1
• Date: Fri, 17 Apr 2026 02:47:31 GMT
• Title: Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models
• Abstract summary: We propose textbfSIF (emphSample Is Feature), which encodes each historical Raw Sample directly into the sequence token.<n>The textbfSample Tokenizer quantizes each historical Raw Sample into a Token Sample via hierarchical group-adaptive quantization.<n>The textbfSIF-Mixer performs deep feature interaction over the homogeneous sample representations via token-level and sample-level mixing, fully unleashing the model's representational capacity.
• Score: 14.332200648147863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling industrial recommender models has followed two parallel paradigms: \textbf{sample information scaling} -- enriching the information content of each training sample through deeper and longer behavior sequences -- and \textbf{model capacity scaling} -- unifying sequence modeling and feature interaction within a single Transformer backbone. However, these two paradigms still face two structural limitations. Firstly, sample information scaling methods encode only a subset of each historical interaction into the sequence token, leaving the majority of the original sample context unexploited and precluding the modeling of sample-level, time-varying features. Secondly, model capacity scaling methods are inherently constrained by the structural heterogeneity between sequential and non-sequential features, preventing the model from fully realizing its representational capacity. To address these issues, we propose \textbf{SIF} (\emph{Sample Is Feature}), which encodes each historical Raw Sample directly into the sequence token -- maximally preserving sample information while simultaneously resolving the heterogeneity between sequential and non-sequential features. SIF consists of two key components. The \textbf{Sample Tokenizer} quantizes each historical Raw Sample into a Token Sample via hierarchical group-adaptive quantization (HGAQ), enabling full sample-level context to be incorporated into the sequence efficiently. The \textbf{SIF-Mixer} then performs deep feature interaction over the homogeneous sample representations via token-level and sample-level mixing, fully unleashing the model's representational capacity. Extensive experiments on a large-scale industrial dataset validate SIF's effectiveness, and we have successfully deployed SIF on the Meituan food delivery platform.

Related papers

• User-Centric Modeling of Transactional Sequences with Explainable State Space Models [0.0]
  We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with State Space Models (SSMs)<n>Experiments on three public datasets demonstrate consistent improvements over standalone Mamba and CoLES with a linear classifier.
  arXiv  Detail & Related papers  (2026-07-22T14:47:25Z)
• SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning [0.0]
  We introduce SetFlow, a generative architecture that models entire Multiple Instance Learning bags directly in the representation space.<n>We evaluate SetFlow on a large-scale mammography benchmark using a state-of-the-art MIL-PF classification pipeline.
  arXiv  Detail & Related papers  (2026-03-20T13:29:26Z)
• From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space [78.36537400975298]
  Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models.<n>We propose Multi-View GRPO, a novel approach that enhances relationship exploration by augmenting the condition space.<n>MV-GRPO achieves superior alignment performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-13T04:35:13Z)
• [MASK] is All You Need [28.90875822599164]
  We propose using discrete-state models to connect Masked Generative and Non-autoregressive Diffusion models.<n>By leveraging [MASK] in discrete-state models, we can bridge Masked Generative and Non-autoregressive Diffusion models.
  arXiv  Detail & Related papers  (2024-12-09T18:59:56Z)
• AEMLO: AutoEncoder-Guided Multi-Label Oversampling [6.255095509216069]
  AEMLO is an AutoEncoder-guided Oversampling technique for imbalanced multi-label data. We show that AEMLO outperforms the existing state-of-the-art methods with extensive empirical studies.
  arXiv  Detail & Related papers  (2024-08-23T14:01:33Z)
• Masked Generative Modeling with Enhanced Sampling Scheme [1.3927943269211591]
  Enhanced Sampling Scheme (ESS) ensures both sample diversity and fidelity. ESS consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling. We demonstrate significant performance gains of ESS in both unconditional sampling and class-conditional sampling.
  arXiv  Detail & Related papers  (2023-09-14T09:42:13Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning [85.55727213502402]
  We focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. We propose Sample-specific Ensemble of Source Models (SESoM) SESoM learns to adjust the contribution of each source model for each target sample separately when ensembling source model outputs.
  arXiv  Detail & Related papers  (2022-10-23T01:33:16Z)
• Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision [75.1860418333995]
  Programmatic Weak Supervision (PWS) has emerged as a widespread paradigm to synthesize training labels efficiently. The core component of PWS is the label model, which infers true labels by aggregating the outputs of multiple noisy supervision sources as labeling functions. Existing statistical label models typically rely only on the outputs of LF, ignoring the instance features when modeling the underlying generative process.
  arXiv  Detail & Related papers  (2022-10-06T07:28:53Z)
• Global Mixup: Eliminating Ambiguity with Clustering [18.876583942942144]
  We propose a novel augmentation method based on global clustering relationships named textbfGlobal Mixup. Experiments show that Global Mixup significantly outperforms previous state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-06-06T16:42:22Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• Set Based Stochastic Subsampling [85.5331107565578]
  We propose a set-based two-stage end-to-end neural subsampling model that is jointly optimized with an textitarbitrary downstream task network. We show that it outperforms the relevant baselines under low subsampling rates on a variety of tasks including image classification, image reconstruction, function reconstruction and few-shot classification.
  arXiv  Detail & Related papers  (2020-06-25T07:36:47Z)

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.