4 papers
Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings
Ekaterina Trushkova, Artur Gimranov, Anton Lysenko
Sequential recommenders typically rely on learnable positional embeddings to encode the order of user interactions. In this work, we ask whether this ordinal signal can be replaced…
Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies
Ekaterina Grishina, Stepan Kuznetsov, Askar Tsyganov +8
The ranking of recommendation algorithms is a challenging problem since model performance is sensitive to dataset characteristics such as sparsity, sequential structure, and scale.…
Cross-Representation Knowledge Transfer for Improved Sequential Recommendations
Artur Gimranov, Viacheslav Yusupov, Elfat Sabitov +4
Transformer architectures, capable of capturing sequential dependencies in the history of user interactions, have become the dominant approach in sequential recommender systems. De…
Ontological model identification based on data from heterogeneous sources
A. Kalinin, E. Shikov, D. Vaganov +1
The development of a company often entails the emergence of autonomous data sources with different structural and technological organization. This can lead to the inability of data…