Zobrazeno 1 - 10
of 12 042
pro vyhledávání: '"A Lio"'
Neural Algorithmic Reasoning (NAR) research has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. However, most previous approaches have always used a recurrent architecture, where each iteration of the GNN m
Externí odkaz:
http://arxiv.org/abs/2410.15059
We develop a novel data-driven framework as an alternative to dynamic flux balance analysis, bypassing the demand for deep domain knowledge and manual efforts to formulate the optimization problem. The proposed framework is end-to-end, which trains a
Externí odkaz:
http://arxiv.org/abs/2410.14426
Hypergraph neural networks are a class of powerful models that leverage the message passing paradigm to learn over hypergraphs, a generalization of graphs well-suited to describing relational data with higher-order interactions. However, such models
Externí odkaz:
http://arxiv.org/abs/2410.07764
Autor:
Duta, Iulia, Liò, Pietro
The importance of higher-order relations is widely recognized in a large number of real-world systems. However, annotating them is a tedious and sometimes impossible task. Consequently, current approaches for data modelling either ignore the higher-o
Externí odkaz:
http://arxiv.org/abs/2410.03208
Autor:
Singh, Vikash, Khanzadeh, Matthew, Davis, Vincent, Rush, Harrison, Rossi, Emanuele, Shrader, Jesse, Lio, Pietro
We present Bayesian Binary Search (BBS), a novel probabilistic variant of the classical binary search/bisection algorithm. BBS leverages machine learning/statistical techniques to estimate the probability density of the search space and modifies the
Externí odkaz:
http://arxiv.org/abs/2410.01771
Heterogeneous graphs, with nodes and edges of different types, are commonly used to model relational structures in many real-world applications. Standard Graph Neural Networks (GNNs) struggle to process heterogeneous data due to oversmoothing. Instea
Externí odkaz:
http://arxiv.org/abs/2409.08036
Neural Algorithmic Reasoning (NAR) aims to optimize classical algorithms. However, canonical implementations of NAR train neural networks to return only a single solution, even when there are multiple correct solutions to a problem, such as single-so
Externí odkaz:
http://arxiv.org/abs/2409.06953
Autor:
Wang, Chong, Li, Mengyao, He, Junjun, Wang, Zhongruo, Darzi, Erfan, Chen, Zan, Ye, Jin, Li, Tianbin, Su, Yanzhou, Ke, Jing, Qu, Kaili, Li, Shuxin, Yu, Yi, Liò, Pietro, Wang, Tianyun, Wang, Yu Guang, Shen, Yiqing
Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model architectures, lacking
Externí odkaz:
http://arxiv.org/abs/2409.00133
Autor:
Bergna, Richard, Calvo-Ordoñez, Sergio, Opolka, Felix L., Liò, Pietro, Hernandez-Lobato, Jose Miguel
We address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODE) are effective in learning node representations, they fail to quantify uncertainty. To address t
Externí odkaz:
http://arxiv.org/abs/2408.16115
Autor:
Shen, Yiqing, Chen, Zan, Mamalakis, Michail, Liu, Yungeng, Li, Tianbin, Su, Yanzhou, He, Junjun, Liò, Pietro, Wang, Yu Guang
The structural similarities between protein sequences and natural languages have led to parallel advancements in deep learning across both domains. While large language models (LLMs) have achieved much progress in the domain of natural language proce
Externí odkaz:
http://arxiv.org/abs/2408.15299