Scaling and Stabilizing Large-Scale Embedding-Based Retrieval

• URL: http://arxiv.org/abs/2607.10096v1
• Date: Sat, 11 Jul 2026 03:24:26 GMT
• Title: Scaling and Stabilizing Large-Scale Embedding-Based Retrieval
• Abstract summary: We present a unified pipeline deployed at Walmart that addresses both signal quality and model evolution.<n>We introduce a Warm-Start Distillation technique that transfers domain-specific expertise from the legacy model to the new backbone.<n>The proposed pipeline is deployed in live production, delivering a +7.34% improvement in NDCG@5 and a +0.50% lift in gross revenue.
• Score: 16.34687313227663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embedding-based retrieval (EBR) is foundational to large-scale e-commerce search, yet its effectiveness is often constrained by the quality of training signals and the representational capacity of the encoder. Standard dual-encoders suffer from a training-inference gap: they are optimized on narrow candidate pools but must discriminate against hundreds of millions of items during inference. Furthermore, while transitioning to higher-capacity backbones can mitigate this gap, simply replacing a mature model can lead to inconsistent retrieval behavior and a loss of the domain-specific knowledge established in previous iterations. In this paper, we present a unified pipeline deployed at Walmart that addresses both signal quality and model evolution. Our contributions are two-fold: (1) Hybrid Hard Negative Mining: We integrate Online Cross-Batch Sampling to increase negative diversity by an order of magnitude and Hybrid Offline Mining, which combines cross-encoder predictions with metadata heuristics to identify nuanced mismatches. (2) Legacy-Aware Distillation: We transition from DistilBERT to a higher-capacity GTE-base encoder. To ensure a smooth and superior transition, we introduce a Warm-Start Distillation technique that transfers domain-specific expertise from the legacy model to the new backbone. Validated through extensive offline experiments and online A/B testing, the proposed pipeline is deployed in live production, delivering a +7.34% improvement in NDCG@5 and a +0.50% lift in gross revenue.

Related papers

• Douyin Multimodal Embedding Model Technical Report [77.9018834072698]
  Multimodal representation learning is a cornerstone of modern AI.<n>We present Douyin Multimodal Embedding (DME), a model trained in two stages to combine both strengths.
  arXiv  Detail & Related papers  (2026-08-03T12:31:49Z)
• MESH: Scaling Up Retrieval with Heterogeneous Content Unification [2.7340856806188447]
  MESH is a unified retrieval scaling framework that mitigates the Scaling Bias of Heterogeneity.<n>By partitioning the feature space into independent domains, MESH enforces a structural inductive bias that reduces interference between sparse-item signals and high-frequency engagement features.<n>Our findings suggest MESH as a promising paradigm for consolidating fragmented retrieval infrastructures into more scalable and ecosystem-aware backbones.
  arXiv  Detail & Related papers  (2026-07-14T06:12:26Z)
• DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction [8.972672149050627]
  Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems.<n>This task presents a modeling challenge: click signals are abundant and exhibit short temporal horizons, whereas conversion signals are inherently sparse, long-delayed, and frequently unattributed.<n>We propose DUET, a framework that explicitly partitions user behavioral data into two domain-coherent streams -- clicks and conversions.
  arXiv  Detail & Related papers  (2026-06-08T23:13:58Z)
• Unlocking High-Fidelity Analog Joint Source-Channel Coding on Standard Digital Transceivers [54.82164616081277]
  D2AJSCC is a novel framework enabling high-fidelity analog J SCC deployment on standard digital PHYs.<n>Our system achieves near-ideal analog J SCC performance with graceful degradation across SNR conditions.<n>By enabling next-generation semantic transmission on legacy infrastructure without hardware modification, our framework promotes sustainable network evolution.
  arXiv  Detail & Related papers  (2026-03-10T01:42:23Z)
• Switch-Hurdle: A MoE Encoder with AR Hurdle Decoder for Intermittent Demand Forecasting [0.0]
  Intermittent demand is a persistent challenge in retail and supply chain forecasting.<n>We introduce Switch-Hurdle: a new framework that integrates a Mixture-of-Experts (MoE) encoder with a Hurdle-based probabilistic decoder.
  arXiv  Detail & Related papers  (2026-02-26T07:03:19Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Apriel-H1: Towards Efficient Enterprise Reasoning Models [6.630534140883356]
  Apriel-H1 family of hybrid LLMs combine transformer attention and SSM sequence mixers for efficient reasoning at 15B model size.<n>We release multiple post-distillation variants of Apriel-H1-15B-Thinker with different SSM-to-MHA ratios and analyse how reasoning performance degrades as more Mamba layers replace MHA.
  arXiv  Detail & Related papers  (2025-11-04T15:17:43Z)
• MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation [44.05859062614669]
  MiniOneRec is the first fully open-source generative recommendation framework.<n>It provides an end-to-end workflow spanning SID construction, supervised fine-tuning, and recommendation-oriented reinforcement learning.<n>Our experiments reveal a consistent downward trend in both training and evaluation losses with increasing model size.
  arXiv  Detail & Related papers  (2025-10-28T13:58:36Z)
• Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation [3.016046646886431]
  DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs.<n>A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.<n> innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance.
  arXiv  Detail & Related papers  (2025-06-02T23:01:15Z)
• Few-Step Diffusion via Score identity Distillation [67.07985339442703]
  Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models.<n>Existing methods rely on real or teacher-synthesized images to perform well when distilling high-resolution T2I diffusion models.<n>We propose two new guidance strategies: Zero-CFG, which disables CFG in the teacher and removes text conditioning in the fake score network, and Anti-CFG, which applies negative CFG in the fake score network.
  arXiv  Detail & Related papers  (2025-05-19T03:45:16Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [80.62659379624867]
  We propose Flow-GRPO, the first method to integrate online policy reinforcement learning into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

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.