Zobrazeno 1 - 10
of 249
pro vyhledávání: '"Cannistraci, Carlo"'
The growing computational demands posed by increasingly number of neural network's parameters necessitate low-memory-consumption training approaches. Previous memory reduction techniques, such as Low-Rank Adaptation (LoRA) and ReLoRA, suffer from the
Externí odkaz:
http://arxiv.org/abs/2405.15481
Hyperbolic networks are supposed to be congruent with their underlying latent geometry and following geodesics in the hyperbolic space is believed equivalent to navigate through topological shortest paths (TSP). This assumption of geometrical congrue
Externí odkaz:
http://arxiv.org/abs/2005.13255
Around 80% of global trade by volume is transported by sea, and thus the maritime transportation system is fundamental to the world economy. To better exploit new international shipping routes, we need to understand the current ones and their complex
Externí odkaz:
http://arxiv.org/abs/2003.13099
Autor:
Ge, Yan, Rosendahl, Philipp, Durán, Claudio, Töpfner, Nicole, Ciucci, Sara, Guck, Jochen, Cannistraci, Carlo Vittorio
Publikováno v:
IEEE/ACM Trans. Comput. Biol. Bioinform (2019)
Despite fluorescent cell-labelling being widely employed in biomedical studies, some of its drawbacks are inevitable, with unsuitable fluorescent probes or probes inducing a functional change being the main limitations. Consequently, the demand for a
Externí odkaz:
http://arxiv.org/abs/2003.00009
Analysis of 'big data' characterized by high-dimensionality such as word vectors and complex networks requires often their representation in a geometrical space by embedding. Recent developments in machine learning and network geometry have pointed o
Externí odkaz:
http://arxiv.org/abs/1907.00025
Publikováno v:
Proceedings of the National Academy of Sciences Jan 2019, 201817880
Network navigability is a key feature of complex networked systems. For a network embedded in a geometrical space, maximization of greedy routing (GR) measures based on the node geometrical coordinates can ensure efficient greedy navigability. In PNA
Externí odkaz:
http://arxiv.org/abs/1901.07909
Publikováno v:
In iScience 20 January 2023 26(1)
Affinity propagation is one of the most effective unsupervised pattern recognition algorithms for data clustering in high-dimensional feature space. However, the numerous attempts to test its performance for community detection in complex networks ha
Externí odkaz:
http://arxiv.org/abs/1804.04566
The idea of minimum curvilinearity (MC) is that the hidden geometry of complex networks, in particular when they are sufficiently sparse, clustered, small-world and heterogeneous, can be efficiently navigated using the minimum spanning tree (MST), wh
Externí odkaz:
http://arxiv.org/abs/1802.01183
Local-ring network automata and the impact of hyperbolic geometry in complex network link-prediction
Topological link-prediction can exploit the entire network topology (global methods) or only the neighbourhood (local methods) of the link to predict. Global methods are believed the best. Is this common belief well-founded? Stochastic-Block-Model (S
Externí odkaz:
http://arxiv.org/abs/1707.09496