2 papers
cs.IR2026
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…
cs.IR2026
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…