🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We have now released the schedule for the Paris Learning on Graphs Meetup on the 30th November at Ecole Polytechnique. bit.ly/LOG-Paris-Sche… You can register to event here: bit.ly/LOG-Paris-Sign… We (Alexandre Duval, Fragkiskos Malliaros & M. Vazirgiannis) look forward to seeing you there!

Super excited to finally release our "Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems" !🤗 Link: arxiv.org/pdf/2312.07511… Written with Chaitanya K. Joshi Simon Mathis Victor Schmidt 💀🐔 Santiago Miret Fragkiskos Malliaros Taco Cohen Pietro Lio, Yoshua Bengio Michael Bronstein 😍 See thread below 👇 (1/8)

"A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems" arxiv.org/abs/2312.07511 Tomorrow in the reading group with Chaitanya K. Joshi Simon Mathis and Alexandre Duval 🤗 Join us at 11am EDT / 5pm CEST on zoom: portal.valencelabs.com/logg

Thank you so much to 100+ of you who tuned it! It was a great pleasure to discuss this little field with all of you! 🤗 Slides are here: chaitjo.com/publication/du… (to be updated soon)

🧵Our paper “Gegenbauer Graph Neural Networks for Time-Varying Signal Reconstruction” was accepted in IEEE Transactions on Neural Networks and Learning Systems (some weeks ago)! 📄 Read it here: doi.org/10.1109/TNNLS.… 📑 ArXiv link: arxiv.org/abs/2403.19800

Predicting causal effects tends to require a high label ratio, which translates to more interventions and hence higher risk/cost. Our paper “Uplift Modelling under Limited Supervision“, accepted ECML PKDD’24, indicates that smaller experiments could suffice in e-commerce.1/2

Very happy to have collaborated on this paper (now accepted at ECML PKDD'24) about uplift modelling in the e-commerce scenario leveraging #GNNs 🚀 Amazing work led by George Panagopoulos and supervised by Fragkiskos Malliaros and Jun Pang 😎

(Big) life update 😊: With Victor Schmidt 💀🐔 & Mathieu Galtier, we are co-founding @Entalpic_ai, an AI startup for chemistry and materials discovery. Our mission is to develop science and its applications for a fair and ecological transition. In stealth but hiring entalpic.notion.site/Entalpic-is-hi…

"Do we really need to drop items with missing modalities in #multimodal #recsys?" Not at all! Our short paper at #CIKM2024 ACM CIKM 2024 proposes untrained #graph propagation to impute missing modalities as a **preprocessing** stage 🚀 w/ Emanuele Rossi Claudio Pomo Fragkiskos Malliaros Tommaso Di Noia

Recently, #diffusion models in CV have been shown to produce possibly #biased images, eventually leading to #unfairness. Thus, a natural question arises: "Does this also occur in #recommendation?" Maybe yes 🫢 Take a look at our pre-print 👇👇 arxiv.org/abs/2409.04339

The internship recruitment season has started! We are pleased to announce several internship positions in the broader field of geometric deep learning, available at CentraleSupélec, Centre Inria de Saclay, Université Paris-Saclay, Télécom Paris, and Institut Polytechnique de Paris.

This year, I have the privilege to co-organize the #LoG2024 Learning on Graphs Conference 2025 meetup in #Paris with amazing colleagues here in Paris 🚀 Date: Nov 29, 2024 Location: Télécom Paris Check out our website, and make sure to follow LoG Meetup Paris to stay tuned for all events!!

We had 2 successful previous editions of the #LoG Learning on Graphs Conference 2025 meetup event in #Paris, with 10+ insightful talks and 15+ amazing poster presentations 😎 Now, we invite you again to submit your proposals to showcase your research in #graph #ML! Form: tinyurl.com/y7fvyb6t

This year, the #LoG2024 Learning on Graphs Conference 2025 meetup event in #Paris will take place in the beautiful Télécom Paris 👩‍🎓 To get ready, let's find out more about the campus 🏢 and how to reach it 🧭 All useful info here👇👇 telecom-paris.fr/en/campus/life…

This week, I’ll attend #CIKM2024 ACM CIKM 2024. A busy schedule ahead 😃 👉 Session chair (#graph #recommendation session) 👉 Short paper (arxiv.org/abs/2408.11767) w/ Emanuele Rossi Claudio Pomo Tommaso Di Noia Fragkiskos Malliaros 👉 Mentor at the PhD symposium See you at the conference!! 🚀🚀🚀

📣 Consider submitting your paper on Network Science and AI to our special session! 📆 Deadline: November 20

We’ve kicked off the #LoG2024 Learning on Graphs Conference 2024 meetup in #Paris with the first session of the day. Florence d’Alché-Buc (Télécom, Institut Polytechnique de Paris) is giving a keynote on: “Supervised Graph Prediction: the key role of loss functions" 🚀 Join us in person and online!

We’re back with the second session. Pascal Welke is giving a keynote on: “Expressive Graph Embeddings via Homomorphism Counting” 🚀 Join us in person and online 🤩 #LoG2024 Learning on Graphs Conference 2024 #Paris

Super happy to see my former PhD student abdulkadir and current postdoc researcher Daniele Malitesta be listed among the top reviewers of Learning on Graphs Conference 2024! Way to go 🚀

The LoG Meetup Paris strikes again 🤩 The 3rd edition happened in Telecom on Friday, with some amazing speakers and plenty of engaged participants. Bonus this year —> I talked about how Entalpic uses GNNs in their materials discovery pipeline 😇⚛️ Learning on Graphs Conference 2024