Serrano Moral

Mariangeles Serrano Moral

University of Barcelona

December 02

7:30 p.m.

CM 1.26

Renormalization of Complex Networks: From Multiscale Self-Similarity to Zero-Shot GNN Transfer

The renormalization group in physics provides a rigorous framework for understanding systems across length scales. Extending these ideas to complex networks, however, is challenging because their small-world structure induces correlations between coexisting scales and obscures the notion of locality. To address this challenge, we have developed geometric renormalization (GR) methods for both unweighted and weighted networks. Building on their mapping into hyperbolic space, GR reveals multiscale self-similarity as a pervasive organizing principle of real-world networks, including human brain connectomes. This self-similarity also emerges in the growth of certain real networks, whose evolution can be interpreted as a reverse renormalization process. Beyond providing a theoretical framework for network organization and evolution, GR enables practical applications. It allows us to generate scaled-down and scaled-up network replicas that preserve structural properties, providing controlled substrates for studying size-dependent processes and large-scale simulations. As a recent application, we have shown that Graph Neural Networks (GNNs) trained on GR scaled-down replicas can be transferred zero-shot to the original networks, preserving much of their predictive performance while substantially reducing training cost. These results suggest that the same multiscale structure that underlies renormalization may also enable learning to generalize across scales.

To register for the dinner enter your name and email address (no spaces or special chars allowed) below before noon on the Tuesday preceding the colloquium

nr.nameemailvegetarian?
1ana achucarroachucar… NO
2Bartosz Kreftb.kreft… YES
3Alexandru Babeanubabeanu… NO
4Carlo Beenakkerbeenakk… NO
5Alessio Catanzarocatanza… NO
6Zhiyuan Chengcheng@p… NO
7Liru Fengfeng@ph… NO
8Mariangeles SerranoMoralfran@lo… NO
9Stefano Gaglianigaglian… NO
10MariaLuisa Gallavottigallavo… NO
11Diego Garlaschelligarlasc… NO
12R Vanbureniceonfi… NO
13Sander Kammeraatkammera… NO
14Koen Kuijkenkuijken… NO
15Keqin Zhaokzhao@s… NO
16Jurriaan Langendorfflangend… NO
17Serge Lemaylemay@p… NO
18Louk Rademakerlouk.ra… NO
19Matthieu Schallermschall… NO
20Mattia Pantiripantiri… NO
21Subodh Patilpatil@l… NO
22Fiammetta Rosenblattrosenbl… NO
23Stefano Pollas.polla… NO
24Wim vanSaarloossaarloo… NO
25Alessandra Silvestrisilvest… NO
26Sai Zhaiszhai@s… NO
27Jitske vanderVlugtvanderv… NO
28Vlad Tkachukvlad@qu… NO
29Ciaran Wareham-Kavanaghwareham… NO
30Xiao Liangxiao@pe… NO
31Xin Zhangxzhang@… NO
32Jakub Tworzydloyakub@l… NO
33Zhibang Yaoyao@lor… NO
34yingjian liuyingjia… NO
35Yuma Watanabeyuma.wa… NO
36Yunhao Zhangyunhaoz… NO
37Vladimir Zakharovzakharo… YES
38Zherui WangZherui.… NO
39Bjorn vanZwolzwolbe@… YES