Antonio Longa

I'm pleased to announce that our paper, titled "Generating Fine-Grained Surrogate Temporal Networks," has been accepted for publication in Communications Physics. In collaboration with @_giuliacencetti @suneman @andrea_whatever @brulepri nature.com/articles/s4200…

🎉 We’re excited to announce IWSDS 2026 will take place Feb 26 – Mar 1, 2026 in Trento🇮🇹! 🏔️✨ 📢 Call for Papers is now open! 🔗 sites.google.com/unitn.it/iwsds… #IWSDS26 #ConversationalAI @UniTrento @UniTrento_DISI

HONAI 2025: Higher-Order Networks meets AI 🍯 is now underway at NetSci 2025! Our first keynote, @maximelca, has just taken the stage.

🔥 Curious about where machine learning meets network science? Join our panel at #NetSci2025 as ML pros and network scientists tackle the big questions: When? Why? How? Discover how these worlds collide—and how to make the most of it. Don't miss out!

Get ready for an explosive mix! 😍 HONAI🍯is Monday, June 2nd, at #NetSci2025! Catch big keynotes from @maximelca  & @chrisbloecker plus many other amazing speakers. See the full program here: hons-web.github.io/online/program… Can't wait to meet you in Maastricht! @NetSciConf

🌐 How do connections evolve over time? Join TENET@CCS25 and dive into Temporal Networks — from traffic routing to epidemic modelling! 🕰️📊 🚀 Share your latest methods, models, & applications. 📝 Abstract deadline: May 15, 2025 📍 Siena, Italy 🇮🇹 sites.google.com/view/tenet-ccs…

In LoCo-LMs, we propose a neuro-symbolic loss function to fine-tune a LM to acquire logically consistent knowledge from a domain graph, i.e. wrt. to a set of logical consistency rules. @looselycorrect @tetraduzione arxiv.org/abs/2409.13724

Faithfulness of GNN explanations isn’t one-size-fits-all🧢 Our last @iclr_conf paper breaks it down across: 1. Evaluation metrics 2. Model implementations 3. OOD generalisation w: @AntonioLonga94 @looselycorrect @andrea_whatever 1/5

Il riscaldamento globale rende l'acqua ancora più preziosa. I grandi data center del Big Tech consumano incredibili quantità di acqua (v. quanto accade in Aragona); un motivo in più per ripensare il consumismo tecnologico e l'AI economy, e per tassare pesantemente il Big Tech.

🚀 Curious about RDL explanations? In this work, @franciferrini_ introduces a novel self-explainable GNN for RDL, leveraging multiple meta-path occurrences! 🔍🤖 Accepted @TmlrOrg! 📄👇 🔗 openreview.net/pdf?id=8Q4qxe9… w/ @andrea_whatever & Manfred Jaeger

🚀 How much can Network Science boost AI? And vice versa? 🤔 Join HONS meets AI workshop at #NetSci2025 to explore these questions! 📢 Submit your work & be part of the discussion! hons-web.github.io/online/ with @alessiaantelmi @ManuelDileo @VincentPGrande @yllka_velaj @vins23p

Explainability in GNNs isn’t just for trust and fairness—it’s a tool for improvement! 📈 Our latest work shows how explainability can be used to regularize GNN training. 📰openreview.net/forum?id=adlpu… at @LogConference With Vincenzo Marco De Luca @pl219_Cambridge @andrea_whatever

⚠️Check out this fascinating initiative! These disciplines address similar problems from different perspectives, and their combination holds great promise.

Graph data is costly to label, but active learning (AL) can help! 💰 We explore several AL techniques for graph-level regression in supervised & unsupervised settings. 🚀 Check it out 📰 sciencedirect.com/science/articl… With @HSamoaa, Linus Aronsson, @xLeitix, Morteza Haghir Chehreghani

🎉 looking forward to an amazing opportunity to connect with researchers in the field!

🚨 Excited to announce our new paper, “SpikeFlow: Automated and Flexible Analysis of ChIP-Seq Data with Spike-in Control”, now online in NAR Genomics and Bioinformatics! 🚨 🔗 academic.oup.com/nargab/article… @LabChiacchiera @aromanel

📢 We've opened a call for two researcher positions on two parallel research lines: a) Human Behaviour in the digital space -- online misinformation and disinformation spreading. b) Human Behaviour in the physical space -- urban mobility and urban digital twins. Please RT! 1/4

And today we are ready to present our poster at #UAI2024! 😎 Polletto also joined us in this adventure, with @andrea_whatever @samubortolotti

Great poster session today at @IC2S2! Thanks to all the people that stopped by. I promise we'll have a preprint out soon! 🤞🤞