Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Pan, Liming"'
A central question in deep learning is how deep neural networks (DNNs) learn features. DNN layers progressively collapse data into a regular low-dimensional geometry. This collective effect of non-linearity, noise, learning rate, width, depth, and nu
Externí odkaz:
http://arxiv.org/abs/2407.19353
Autor:
Bardella, Giampiero, Franchini, Simone, Pan, Liming, Balzan, Riccardo, Ramawat, Surabhi, Brunamonti, Emiliano, Pani, Pierpaolo, Ferraina, Stefano
Publikováno v:
Entropy 2024, 26(6), 495
Brain-computer interfaces surged extraordinary developments in recent years, and a significant discrepancy now exists between the abundance of available data and the limited headway made in achieving a unified theoretical framework. This discrepancy
Externí odkaz:
http://arxiv.org/abs/2310.09178
Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit the dynamics with a graph neural network (GNN) on a learnable graph. They use one-step message-pas
Externí odkaz:
http://arxiv.org/abs/2306.06041
Graph neural networks (GNNs) excel in modeling relational data such as biological, social, and transportation networks, but the underpinnings of their success are not well understood. Traditional complexity measures from statistical learning theory f
Externí odkaz:
http://arxiv.org/abs/2212.13069
Previous studies show that recommendation algorithms based on historical behaviors of users can provide satisfactory recommendation performance. Many of these algorithms pay attention to the interest of users, while ignore the influence of social rel
Externí odkaz:
http://arxiv.org/abs/2206.13072
Autor:
Li, Ruiqi, Luo, Ankang, Shang, Fan, Lv, Linyuan, Fan, Jingfang, Lu, Gang, Pan, Liming, Tian, Lixin, Stanley, H. Eugene
Fundamental laws of human mobility have been extensively studied, yet we are still lacking a comprehensive understanding of the mobility patterns of sharing conveyances. Since travellers would highly probably no longer possess their own conveyances i
Externí odkaz:
http://arxiv.org/abs/2202.06352
Publikováno v:
In Information Sciences August 2024 677
Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-art methods based on subgraph classification label nodes with distance
Externí odkaz:
http://arxiv.org/abs/2110.04375
Interactions in biology and social systems are not restricted to pairwise but can take arbitrary sizes. Extensive studies have revealed that the arbitrary-sized interactions significantly affect the spreading dynamics on networked systems. Competing
Externí odkaz:
http://arxiv.org/abs/2105.08234
While links in simple networks describe pairwise interactions between nodes, it is necessary to incorporate hypernetworks for modeling complex systems with arbitrary-sized interactions. In this study, we focus on the hyperlink prediction problem in h
Externí odkaz:
http://arxiv.org/abs/2103.08926