6 papers
Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
Andrei Chernov, Haroon Wahab, Oleg Novitskij
In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing…
BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting
Andrei Chernov, Vitaliy Pozdnyakov, Ilya Makarov
Recent work in time series forecasting has explored reformulating regression as a classification task. By discretizing the continuous target space into bins and predicting over a f…
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE
Andrei Chernov, Oleg Novitskij
Recent studies have shown that reducing symmetries in neural networks enhances linear mode connectivity between networks without requiring parameter space alignment, leading to imp…
Evaluating Expert Contributions in a MoE LLM for Quiz-Based Tasks
Andrei Chernov
Recently, Large Language Models (LLMs) with Mixture of Experts (MoE) layers have gained significant attention. Currently, state-of-the-art LLMs utilize this architecture. There is…
(GG) MoE vs. MLP on Tabular Data
Andrei Chernov
In recent years, significant efforts have been directed toward adapting modern neural network architectures for tabular data. However, despite their larger number of parameters and…
Fine-Tuning a Time Series Foundation Model with Wasserstein Loss
Andrei Chernov
Inspired by recent advancements in large language models (LLMs) for Natural Language Processing (NLP), there has been a surge in research focused on developing foundational models…