Výsledky vyhledávání

Report

Hypergraph Neural Networks Reveal Spatial Domains from Single-cell Transcriptomics Data

The task of spatial clustering of transcriptomics data is of paramount importance. It enables the classification of tissue samples into diverse subpopulations of cells, which, in turn, facilitates the analysis of the biological functions of clusters,

Externí odkaz: http://arxiv.org/abs/2410.19868

Zobrazit plný text záznamu

Report

Hyperedge Modeling in Hypergraph Neural Networks by using Densest Overlapping Subgraphs

Autor: Soltani, Mehrad, Rueda, Luis

Hypergraphs tackle the limitations of traditional graphs by introducing {\em hyperedges}. While graph edges connect only two nodes, hyperedges connect an arbitrary number of nodes along their edges. Also, the underlying message-passing mechanisms in

Externí odkaz: http://arxiv.org/abs/2409.10340

Zobrazit plný text záznamu

Report

Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks

Autor: Sargolzaei, Saleh, Rueda, Luis

This study explores the potential of Modern Hopfield Networks (MHN) in improving the ability of computer vision models to handle out-of-distribution data. While current computer vision models can generalize to unseen samples from the same distributio

Externí odkaz: http://arxiv.org/abs/2408.11309

Zobrazit plný text záznamu

Report

Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems

Autor: Ebrat, Danial, Rueda, Luis

Training reinforcement learning-based recommender systems are often hindered by the lack of dynamic and realistic user interactions. Lusifer, a novel environment leveraging Large Language Models (LLMs), addresses this limitation by generating simulat

Externí odkaz: http://arxiv.org/abs/2405.13362

Zobrazit plný text záznamu