Universal structural patterns in sparse recurrent neural networks

XJ Zhang, JM Moore, G Yan, X Li - Communications Physics, 2023 - nature.com
Sparse neural networks can achieve performance comparable to fully connected networks
but need less energy and memory, showing great promise for deploying artificial intelligence …

Link Polarity Prediction from Sparse and Noisy Labels via Multiscale Social Balance

M Minici, F Cinus, F Bonchi, G Manco - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
Signed Graph Neural Networks (SGNNs) have recently gained attention as an effective tool
for several learning tasks on signed networks, ie, graphs where edges have an associated …

Which group do you belong to? sentiment-based pagerank to measure formal and informal influence of nodes in networks

L Jiang, L Dinh, R Rezapour, J Diesner - … IX: Volume 2, Proceedings of the …, 2021 - Springer
Organizational networks are often hierarchical by nature as individuals take on roles or
functions at various job levels. Prior studies have used either text-level (eg, sentiment, affect) …

From user-generated text to insight context-aware measurement of social impacts and interactions using natural language processing

R Rezapour - 2021 - ideals.illinois.edu
Abstract" Recent improvements in information and communication technologies have
contributed to an increasingly globalized and connected world. The digital data that are …

Advances to network analysis theories and methods for the understanding of formal and emergent structures in interpersonal, corporate/organizational, and hazards …

L Dinh - 2022 - ideals.illinois.edu
Network analysis provides valuable theoretical and methodological approaches to
investigate complex systems of social-technical relations. Network analysis has been …