Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem

• URL: http://arxiv.org/abs/2607.26365v1
• Date: Wed, 29 Jul 2026 00:44:25 GMT
• Title: Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem
• Abstract summary: This paper compares pretrained industrial graph neural network item embeddings with end-to-end trainable item embeddings across two production recommendation systems at Yandex: Yandex Market and Yandex Music.<n>Our results show that a separate pretraining stage helps when training data is limited, but provides no worthwhile benefit for large-scale models trained on extensive datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based sequential recommendation models, which process sequences of user-item interactions, rely heavily on the item embedding strategy. Existing approaches either use pretrained item embeddings or learn them end-to-end with the transformer. To the best of our knowledge, no prior work has compared these options from both cost and quality perspectives in a large-scale industrial setting. This paper is a case study that compares pretrained industrial graph neural network item embeddings with end-to-end trainable item embeddings across two mature production recommendation systems at Yandex: Yandex Market and Yandex Music. We additionally evaluate both approaches on a low-resource dataset sampled from Yandex Lavka production logs, for which both the data and code are publicly available for demonstration purposes. Our results show that a separate pretraining stage helps when training data is limited, but provides no worthwhile benefit for large-scale models trained on extensive datasets.

Related papers

• Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search [51.30225948318648]
  Generalist Text Embedding Models (GTEs) are pre-trained on large-scale corpora.<n>We show that GTEs can guarantee strong zero-shot performance without specialized adaptation.<n>We also show that compressing embedding dimensions by focusing on the most informative directions effectively reduces noise.
  arXiv  Detail & Related papers  (2025-07-07T13:41:52Z)
• CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training [63.07024608399447]
  We propose an automated framework that discovers, evaluates, and refines data mixtures in a pre-training setting.<n>We introduce ClimbLab, a filtered 1.2-trillion-token corpus with 20 clusters as a research playground, and ClimbMix, a compact yet powerful 400-billion-token dataset.
  arXiv  Detail & Related papers  (2025-04-17T17:58:13Z)
• DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data [61.62554324594797]
  We propose DreamMask, which explores how to generate training data in the open-vocabulary setting, and how to train the model with both real and synthetic data.<n>In general, DreamMask significantly simplifies the collection of large-scale training data, serving as a plug-and-play enhancement for existing methods.<n>For instance, when trained on COCO and tested on ADE20K, the model equipped with DreamMask outperforms the previous state-of-the-art by a substantial margin of 2.1% mIoU.
  arXiv  Detail & Related papers  (2025-01-03T19:00:00Z)
• 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)
• NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models [38.41524186248607]
  We introduce NV-Embed, incorporating architectural designs, training procedures, and curated datasets.<n>For model architecture, we propose a latent attention layer to obtain pooled embeddings.<n>For training algorithm, we introduce a two-stage contrastive instruction-tuning method.
  arXiv  Detail & Related papers  (2024-05-27T17:59:45Z)
• Noisy Self-Training with Synthetic Queries for Dense Retrieval [49.49928764695172]
  We introduce a novel noisy self-training framework combined with synthetic queries. Experimental results show that our method improves consistently over existing methods. Our method is data efficient and outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-11-27T06:19:50Z)
• Opinion mining using Double Channel CNN for Recommender System [0.0]
  We present an approach for sentiment analysis with a deep learning model and use it to recommend products. A two-channel convolutional neural network model has been used for opinion mining, which has five layers and extracts essential features from the data. Our proposed method has reached 91.6% accuracy, significantly improved compared to previous aspect-based approaches.
  arXiv  Detail & Related papers  (2023-07-15T13:11:18Z)
• Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval [152.3504607706575]
  This research aims to conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and define two real practical instance-level retrieval tasks. We exploit to train a more effective cross-modal model which is adaptively capable of incorporating key concept information from the multi-modal data.
  arXiv  Detail & Related papers  (2022-06-17T15:40:45Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)
• Learning to Rank in the Position Based Model with Bandit Feedback [3.9121134770873742]
  We propose novel extensions of two well-known algorithms viz. LinUCB and Linear Thompson Sampling to the ranking use-case. To account for the biases in a production environment, we employ the position-based click model.
  arXiv  Detail & Related papers  (2020-04-27T19:12:20Z)

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.