Taxonomy-based Negative Sampling In Personalized Semantic Search for E-commerce

• URL: http://arxiv.org/abs/2511.00694v1
• Date: Sat, 01 Nov 2025 20:25:00 GMT
• Title: Taxonomy-based Negative Sampling In Personalized Semantic Search for E-commerce
• Authors: Uthman Jinadu, Siawpeng Er, Le Yu, Chen Liang, Bingxin Li, Yi Ding, Aleksandar Velkoski,
• Abstract summary: We present a semantic retrieval model for e-commerce search that embeds queries and products into a shared vector space.<n>To further tailor retrievals, we incorporate user-level personalization by modeling each customer's past purchase history and behavior.
• Score: 46.251483528080236
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large retail outlets offer products that may be domain-specific, and this requires having a model that can understand subtle differences in similar items. Sampling techniques used to train these models are most of the time, computationally expensive or logistically challenging. These models also do not factor in users' previous purchase patterns or behavior, thereby retrieving irrelevant items for them. We present a semantic retrieval model for e-commerce search that embeds queries and products into a shared vector space and leverages a novel taxonomy-based hard-negative sampling(TB-HNS) strategy to mine contextually relevant yet challenging negatives. To further tailor retrievals, we incorporate user-level personalization by modeling each customer's past purchase history and behavior. In offline experiments, our approach outperforms BM25, ANCE and leading neural baselines on Recall@K, while live A/B testing shows substantial uplifts in conversion rate, add-to-cart rate, and average order value. We also demonstrate that our taxonomy-driven negatives reduce training overhead and accelerate convergence, and we share practical lessons from deploying this system at scale.

Related papers

• Intention-Conditioned Flow Occupancy Models [80.42634994902858]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Scaling Sequential Recommendation Models with Transformers [0.0]
  We take inspiration from the scaling laws observed in training large language models, and explore similar principles for sequential recommendation.<n> Compute-optimal training is possible but requires a careful analysis of the compute-performance trade-offs specific to the application.<n>We also show that performance scaling translates to downstream tasks by fine-tuning larger pre-trained models on smaller task-specific domains.
  arXiv  Detail & Related papers  (2024-12-10T15:20:56Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation [48.75470418596875]
  Training on large-scale datasets can boost the performance of video instance segmentation while the datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity. We conduct extensive evaluations on four popular and challenging benchmarks, including YouTube-VIS 2019, YouTube-VIS 2021, OVIS, and UVO. Our model shows significant improvement over the baseline solutions, and sets new state-of-the-art records on all benchmarks.
  arXiv  Detail & Related papers  (2023-12-11T18:50:09Z)
• Multi-output Headed Ensembles for Product Item Classification [0.9053163124987533]
  We propose a deep learning based classification model framework for e-commerce catalogs. We show improvements against robust industry standard baseline models. We also propose a novel way to evaluate model performance using user sessions.
  arXiv  Detail & Related papers  (2023-07-29T01:23:36Z)
• Unified Embedding Based Personalized Retrieval in Etsy Search [0.206242362470764]
  We propose learning a unified embedding model incorporating graph, transformer and term-based embeddings end to end. Our personalized retrieval model significantly improves the overall search experience, as measured by a 5.58% increase in search purchase rate and a 2.63% increase in site-wide conversion rate.
  arXiv  Detail & Related papers  (2023-06-07T23:24:50Z)
• Consistent Text Categorization using Data Augmentation in e-Commerce [1.558017967663767]
  We propose a new framework for consistent text categorization. Our goal is to improve the model's consistency while maintaining its production-level performance.
  arXiv  Detail & Related papers  (2023-05-09T12:47:28Z)
• Generating Negative Samples for Sequential Recommendation [83.60655196391855]
  We propose to Generate Negative Samples (items) for Sequential Recommendation (SR) A negative item is sampled at each time step based on the current SR model's learned user preferences toward items. Experiments on four public datasets verify the importance of providing high-quality negative samples for SR.
  arXiv  Detail & Related papers  (2022-08-07T05:44:13Z)
• PreSizE: Predicting Size in E-Commerce using Transformers [76.33790223551074]
  PreSizE is a novel deep learning framework which utilizes Transformers for accurate size prediction. We demonstrate that PreSizE is capable of achieving superior prediction performance compared to previous state-of-the-art baselines. As a proof of concept, we demonstrate that size predictions made by PreSizE can be effectively integrated into an existing production recommender system.
  arXiv  Detail & Related papers  (2021-05-04T15:23:59Z)
• Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search [29.881612817309716]
  We design an end-to-end First-and-Second-order Relevance prediction model for e-commerce item relevance. We introduce external knowledge generated from BERT to refine the network of user behaviors. Results of offline experiments showed that the new model significantly improved the prediction accuracy in terms of human relevance judgment.
  arXiv  Detail & Related papers  (2021-01-13T03:12:53Z)
• Reinforced Negative Sampling over Knowledge Graph for Recommendation [106.07209348727564]
  We develop a new negative sampling model, Knowledge Graph Policy Network (kgPolicy), which works as a reinforcement learning agent to explore high-quality negatives. kgPolicy navigates from the target positive interaction, adaptively receives knowledge-aware negative signals, and ultimately yields a potential negative item to train the recommender.
  arXiv  Detail & Related papers  (2020-03-12T12:44:30Z)

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.