GOKU improves GNN accuracy by reconstructing a denser latent graph and then spectrally sparsifying it, preserving the original spectrum and edge count while improving connectivity.
Models, Entropy and Information of Temporal Social Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Temporal social networks are characterized by {heterogeneous} duration of contacts, which can either follow a power-law distribution, such as in face-to-face interactions, or a Weibull distribution, such as in mobile-phone communication. Here we model the dynamics of face-to-face interaction and mobile phone communication by a reinforcement dynamics, which explains the data observed in these different types of social interactions. We quantify the information encoded in the dynamics of these networks by the entropy of temporal networks. Finally, we show evidence that human dynamics is able to modulate the information present in social network dynamics when it follows circadian rhythms and when it is interfacing with a new technology such as the mobile-phone communication technology.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
GOKU improves GNN accuracy by reconstructing a denser latent graph and then spectrally sparsifying it, preserving the original spectrum and edge count while improving connectivity.