Jekyll2025-01-21T20:54:13-08:00https://migalkin.github.io/feed.xmlMichael GalkinResearch Scientist @ Intel | ex MilaMichael Galkinmgalkin at google dot comGraph Learning Tutorial @ ICML 20242024-07-22T00:00:00-07:002024-07-22T00:00:00-07:00https://migalkin.github.io/posts/2024/07/22/icmltutParticipated (online) in the panel discussion with Bryan Perozzi, Michael Bronstein, and Christopher Morris on graph foundation models held during the Graph Learning Tutorial at ICML 2024, thanks Ameya and Adrian for inviting!

]]>Michael Galkinmgalkin at google dot comFoundation Models in Graph & Geometric Deep Learning2024-06-18T00:00:00-07:002024-06-18T00:00:00-07:00https://migalkin.github.io/posts/2024/06/18/gfmsIn our new Medium blogpost with Michael Bronstein, Jianan Zhao, Haitao Mao, and Zhaocheng Zhu we discuss foundation models in Graph & Geometric DL: from the core theoretical and data challenges to the most recent models that you can try already today!

]]>Michael Galkinmgalkin at google dot comVisiting WWW and National University of Singapore2024-05-15T00:00:00-07:002024-05-15T00:00:00-07:00https://migalkin.github.io/posts/2024/05/15/singaporeA productive week in Singapore! First, gave a keynote at the workshop on Graph Foundation Models at The WebConf 2024 and participated in the panel discussion. Then, visited the group of professor Xavier Bresson at the National University of Singapore with the talk on graph foundation models - from KG reasoning to AI 4 Science. Thank you Professor Bresson for extending the invitation! Slides

]]>Michael Galkinmgalkin at google dot comPaper accepted at ICML 20242024-05-08T00:00:00-07:002024-05-08T00:00:00-07:00https://migalkin.github.io/posts/2024/05/08/icml24Our position paper Graph Foundation Models are Already Here was accepted at ICML 2024 as a spotlight paper!

]]>Michael Galkinmgalkin at google dot comFANeSy Workshop in Santiago, Chile2024-03-04T00:00:00-08:002024-03-04T00:00:00-08:00https://migalkin.github.io/posts/2024/03/04/fanesyIt was a delightful experience to participate in the week-long workshop on GNNs and neuro-symbolic AI (FANeSy) organized by Pablo Barcelo, CENIA, and Unversidad San Sebastian. Thanks Pablo for the invitation!

]]>Michael Galkinmgalkin at google dot comPaper accepted at ICLR 20242024-01-16T00:00:00-08:002024-01-16T00:00:00-08:00https://migalkin.github.io/posts/2024/01/16/iclr24Our paper on ULTRA, the first foundation model for KG reasoning, was accepted at ICLR 2024. See you in Vienna!

]]>Michael Galkinmgalkin at google dot comGraph & Geometric ML in 2024: Where We Are and What’s Next2024-01-15T00:00:00-08:002024-01-15T00:00:00-08:00https://migalkin.github.io/posts/2024/01/15/reviewTogether with Michael Bronstein, we wrote a huge blog post on the state of affairs in Graph and Geometric DL in 2023 with some predictions for 2024. Part I focuses on theory and GNN architectures (including graph transformers), Part II talks about cool and exciting applications in structured biology, materials science, ML potentials, algorithmic reasoning, and temporal graph learning. We interviewed many prominent researchers to provide several points of view on each subject - so this work wouldn’t be possible without the massive community engagement!

]]>Michael Galkinmgalkin at google dot comDagstuhl and UCSD talks2023-12-23T00:00:00-08:002023-12-23T00:00:00-08:00https://migalkin.github.io/posts/2023/12/23/talksA few talks on graph foundation models given recently: at UC San Diego and at the Dagstuhl seminar on Scalable Graph Mining and Learning.

]]>Michael Galkinmgalkin at google dot comRelease of ULTRA2023-10-23T00:00:00-07:002023-10-23T00:00:00-07:00https://migalkin.github.io/posts/2023/10/23/ultraHappy to release ULTRA - the first foundation model for knowledge graph reasoning. A single pre-trained ULTRA model is able to do zero-shot link prediction on any unseen KG and do so better than many supervisedly trained baselines on 50+ datasets! More details in the Medium blog post. We release the paper, several checkpoints (177k params), code, and data on GitHub and HuggingFace Spaces.

]]>Michael Galkinmgalkin at google dot com2 papers accepted at NeurIPS 20232023-09-21T00:00:00-07:002023-09-21T00:00:00-07:00https://migalkin.github.io/posts/2023/09/21/neurips23papersOur team got two papers accepted at the upcoming NeurIPS’23 in New Orleans!

  • A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs. Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin, Sophie Xhonneux, Ming Zhang, Maxime Gazeau, Jian Tang. preprint
  • Improving Systematic Generalization using Iterated Learning and Simplicial Embeddings. Yi Ren, Samuel Lavoie, Mikhail Galkin, Danica J. Sutherland, Aaron Courville.

See you at NeurIPS! :wink:

]]>Michael Galkinmgalkin at google dot com