Steve Azzolin

Excited to share that I will co-organize with @toniwuest, @cc_jalvarez, @andrea_whatever, @annamonreale and @KatyaTentori the fourth edition of the Hybrid Human-Machine Learning and Decision Making (HLDM’26) @ECMLPKDD in Naples. 👇 1/2

📢 LoG 2026 Organizer Recruitment We are recruiting new organizers to help support the Learning on Graphs 2026 conference and community. Apply here: 🔗 forms.gle/XX2KWe98YJQc8P… 🗓 Deadline: March 16 Please share with anyone in the graph learning community who may be interested!

My PhD student & I are studying if XAI heatmaps really help humans understand what AI "sees" in image classification. It takes max 10 min, fully anonymous, no login. Help us improve explainable AI — just a few clicks! emirhanbilgic.github.io/web_applicatio… Thanks! #XAI #AI #Computervision

The conference may be over, but the LOG community never slows down 🧑‍💼🌍 Join us at upcoming meetups worldwide: 🇳🇴 Tromsø 🇮🇳 Gandhinagar 🇮🇹 Pisa 🇫🇷 Paris 🇧🇷 São arlos 🇮🇳 New Delhi

@barbera_cesare felicitaciones, bien hecho

Very excited for my first work! See you in Tangiers 🐋🌴☀️ #AISTATS2026 #calibration

I’m not crying, I just got a concept in my eye

Join us at LoG 2025 (Dec 10–12)! 🗓️Keynotes on graph learning & geometry from Aditi Krishnapriyan (Day1⃣), Haggai Maron (Day2⃣), Michael Galkin & Melanie Weber (Day3⃣) — from molecular ML to neural artifacts & graph foundation models. Register now: logconference.org/register/

📢 Now that we have an in-person LoG, why are we still supporting meetups? 👉 Meetups keep the community alive all year round, beyond the main event 👉 They give the community more chances to connect locally and inclusively 👉 They complement—not compete with—the in-person LoG

🚀 The LoG 2025 volunteer application is open! Give 2 hours → get FREE conference registration. Connect with researchers worldwide and help make LoG 2025 welcoming and successful. 🌍🤝 Apply now ➡️ forms.gle/R9AG7c6raTxJ2K… #LoG2025 #Volunteer #AI #ML

📢LoG 2025 Registration📢 👤 Venue: Arizona State University, Phoenix, AZ 🚨 For each accepted paper/tutorial, at least one author must attend in person: #attendance-policy" target="_blank" rel="nofollow noopener">logconference.org/cfp/#attendanc… 🔗 Registration details: logconference.org/register/

✨Call for organising local meetups is now out✨ We continue our mission to support a thriving network of local, researcher-driven events 📢 Join our network and submit a proposal: logconference.org/call-for-meetu… 🗓️Deadline: 10th November

📢 Call for Tutorials – LoG 2025 Learning on Graphs Conference, Dec 10 logconference.org/call-for-tutor… 🗓 Key dates (AoE): • Sept 17 – Proposal deadline • Oct 1 – Notification • Nov 3 – Final materials • Dec 10 – Tutorials Submit your proposal & join us! #LoG2025

In case you missed it, we're still taking self-nominations for reviewers at LoG 2025✍️

Join the Temporal Graph Learning Workshop at KDD 2025, we have an amazing program with great speakers and papers waiting for you. Let's shape together the future of temporal graph research. 📍Aug 4 | 1–5 PM | Room 714A, Toronto Convention Center 🔗 sites.google.com/view/tgl-works…

Ready to present your latest work? The Call for Papers for #UniReps2025 @NeurIPSConf is open! 👉Check the CFP: unireps.org/2025/call-for-… 🔗 Submit your Full Paper or Extended Abstract here: openreview.net/group?id=NeurI… Speakers and panelists: @d_j_sutherland @elmelis @KriegeskorteLab @yuqirose @evadyer @neuro_kim

🚨 Calling all ML & AI companies! The LOG 2025 sponsor page is now live: logconference.org/sponsors/ LOG is the go-to venue for graph ML, reasoning & systems research. We're inviting sponsors to support this fast-growing community & gain visibility. #LOG2025 #GraphML #MachineLearning

Paper: openreview.net/forum?id=mkqcU…

What can we do to make self-explanations less ambiguous? -> We propose to automatically adapt explanations to the task by stitching together SE-GNNs with white-box models and combining their explanations.

Studying some popular models, we found that: - The information that self-explanations convey can radically change based on the underlying task to be explained, which is, however, generally unknown