Search Results for author: Maciej Kula

Found 3 papers, 2 papers with code

Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems

no code implementations10 Nov 2023 Huan Gui, Ruoxi Wang, Ke Yin, Long Jin, Maciej Kula, Taibai Xu, Lichan Hong, Ed H. Chi

We identify two key challenges for applying the vanilla Transformer architecture to web-scale recommender systems: (1) Transformer architecture fails to capture the heterogeneous feature interactions in the self-attention layer; (2) The serving latency of Transformer architecture might be too high to be deployed in web-scale recommender systems.

Recommendation Systems

Binary Latent Representations for Efficient Ranking: Empirical Assessment

2 code implementations22 Jun 2017 Maciej Kula

Large-scale recommender systems often face severe latency and storage constraints at prediction time.

Recommendation Systems

Metadata Embeddings for User and Item Cold-start Recommendations

4 code implementations30 Jul 2015 Maciej Kula

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors.


Cannot find the paper you are looking for? You can Submit a new open access paper.