Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem
arXiv:2607.26365
The paper compares pretrained graph neural network item embeddings with end‑to‑end trainable embeddings in transformer‑based sequential recommendation systems at Yandex, finding pretraining helps only when training data is limited.
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.