PyTorch Geometric Temporal received a Best Paper Nomination at CIKM 2021. Special thanks to Paul Scherer, Yixuan He, George Panagopoulos, Maria Astefanoaei, Olivér Kiss, Ferenc Beres, Nico Collignon, Rik Sarkar. Paper: bit.ly/3jDgyOa Git: bit.ly/3EknBTw

#BREAKING We are super excited to host Prof. #JohnIoannidis, physician, writer and one of the top cited scientists in the world. He will give a talk entitled “Meta-Research and the Quest for Better Science” on November 10th École polytechnique. Save the date! 👉bit.ly/2ZjO1WO

Congratulations to all the authors for their papers nominated for best resource paper at #CIKM2021 Special congratulations to the best resource paper: "PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models"

PyTorch Geometric Temporal received the Resource Track Best Paper Award CIKM 2021!! Special thanks to Paul Scherer, Yixuan He, George Panagopoulos, Maria Astefanoaei, Olivér Kiss, Ferenc Beres, Nico Collignon, Rik Sarkar. Paper: bit.ly/3jDgyOa Git: bit.ly/31vNW2V

[#EVENT] A huge thanks to Prof. #JohnIoannidis for his inspirational talk on "Meta-Research and the Quest for Better Science" École polytechnique @IP__Paris 👏 A memorable afternoon full of enlightening insights and meaningful exchanges🎊🎆

I am very excited to announce I started as an applied scientist in the Algorithms and Optimization Lab of Amazon transportation services!

I made an intro to ML for causal inference and added my two cents for interesting directions geopanag.github.io/blog/2023/08/0…

The Johnson-Lindenstrauss lemma shows that one can project linearly m points in dimension log(m)/epsilon^2 with distortion epsilon. en.wikipedia.org/wiki/Johnson%E…

Excited that our paper entitled “Neural Ordinary Differential Equations for Modeling Epidemic Spreading” with Giannis Nikolentzos, George Panagopoulos, Jean-Marc Steyaert and M. Vazirgiannis, has been accepted for publication at the TMLR journal. x.com/TmlrPub/status…

Prediction-powered inference was published today as a research article in Science! Science Magazine science.org/doi/full/10.11… Check it out - and if ur interested in collaborating, learning about PPI, or ML for science more broadly, plz reach out! Also see Berkeley News

Consider applying to LOGML, one of the premier summer schools in graph/geometric deep learning. I'll be mentoring a project on GNNs for causal inference. See you in London!

In Vienna for #ICLR2024! Meet us w/ George Panagopoulos 📌Halle B#29 (Thu Morn.) We present our TMLR paper (w/M. Vazirgiannis,Giannis Nikolentzos,JM.Steyaert): iclr.cc/virtual/2024/p… - We present a Neural ODE-based model for improved generalization in predicting epidemic spreading on graphs.

1/3 Recently, the Kolmogorov-Arnold networks (KAN) were introduced as an alternative to the traditional multi-layer perceptron (MLP). In our new paper: "KAGNNs: KANs meet Graph Learning" we provide extensively compare KAN-based and MLP-based models on graph-learning tasks.

🎓 And that's a wrap on the LOGML Summer School! 🥰 It was an incredible experience organizing it. A huge thank you to all our speakers for their insightful talks, to our mentors for making it an unforgettable experience for the students, and to all of you for attending! 👏

👋I am on the academic job market, looking for tenure-track positions. I work on machine learning, decision making, and social aspects of AI. Let's get in touch if your institution is hiring! 💻stsirtsis.github.io 😀Shares are very much appreciated!

🚨We are seeking a motivated PhD candidate to join our team at the University of Luxembourg. The successful applicant will engage in cutting-edge research in the field of Topological Deep Learning. Key Details: emea3.mrted.ly/3t5g9 #PhDPosition #OpenPosition

Efficient Data Selection for Training Genomic Perturbation Models - A new study proposes innovative graph-based one-shot data selection methods for training gene expression models, designed to overcome limitations of current active learning techniques. - The main issue with

Metrics to Detect Small-Scale and Large-Scale Citation Concentration Patterns from Iakovos Evdaimon Giannis Nikolentzos Michail Chatzianastasis George Panagopoulos M. Vazirgiannis École polytechnique MBZUAI is part of Day 1’s ‘Research Misconduct and Integrity’ session Register at peerreviewcongress.org!