5 papers
Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression
Viacheslav Yusupov, Daria Cherniuk, Evgeny Frolov
In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer interactions without storing the entire Fisher matrix, enabling practical Hessian analy…
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…
Ultra Fast Warm Start Solution for Graph Recommendations
Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov
In this work, we present a fast and effective Linear approach for updating recommendations in a scalable graph-based recommender system UltraGCN. Solving this task is extremely imp…
Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov
Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a nove…
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov
In this paper, we propose a new geometric approach for knowledge graph completion via low rank tensor approximation. We augment a pretrained and well-established Euclidean model ba…