BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ISISLab - ECPv6.3.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:ISISLab
X-ORIGINAL-URL:https://www.isislab.it
X-WR-CALDESC:Eventi per ISISLab
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Rome
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Rome:20260626T150000
DTEND;TZID=Europe/Rome:20260626T160000
DTSTAMP:20260914T174335
CREATED:20260623T093929Z
LAST-MODIFIED:20260623T093931Z
UID:51157-1782486000-1782489600@www.isislab.it
SUMMARY:Seminar: "Denoising Diffusion for Hypergraph Generation" by Valerio Di Pasquale
DESCRIPTION:Abstract:Hypergraphs make it possible to model higher-order relationships that standard graphs are unable to express. However\, producing realistic hypergraphs is still difficult\, since current approaches often depend on predefined structural constraints or fail to capture the intertwined dependencies between nodes and hyperedges. We present Janus\, a latent diffusion-based framework that partitions an observed hypergraph into sub-hypergraphs\, learns joint latent representations of nodes and hyperedges using a dual-view β-VAE\, and synthesizes new hypergraph structures through paired latent diffusion guided by cross-view conditioning. The framework can perform both unconstrained generation and generation conditioned on a given node set. We further propose an evaluation protocol that assesses interactions at micro\, meso\, and macro levels\, together with structural reconstruction and higher-order similarity metrics. Experiments on five real-world datasets against nine baselines show that Janus delivers the most consistent performance across structural scales\, achieving notable improvements in meso-scale and higher-order fidelity. Under node-set constraints\, it also consistently attains the strongest reconstruction performance.
URL:https://www.isislab.it/event/seminar-denoising-diffusion-for-hypergraph-generation-by-valerio-di-pasquale/
CATEGORIES:Evento
ATTACH;FMTTYPE=image/png:https://www.isislab.it/wp-content/uploads/2026/06/Seminar-26-06-2026.png
END:VEVENT
END:VCALENDAR