Последние посты
Graph Machine Learning
18 мар., 15:19
🚀 LOGML 2026 — Mentor Applications Open (Deadline extended!)The LOGML (London Geometry and Machine Learning) Summer School is a research-focused program bringing together researchers in graph ML, geometric deep learning, and scientific ML to work on open problems.The mentor application deadline has been extended to March 22 (AoE).They are looking for mentors to lead small, high-energy research groups:📍 Imperial College London 📅 July 13–17, 2026Mentors will: • Lead a team of strong students (mostly PhD-level) • Develop research ideas during the school • Build collaborations beyond the event✈️ Travel & accommodation support available🔗 Apply: https://www.logml.ai/apply.htmlwww.logml.aiLOGML 2026London Geometry and Machine Learning Summer School, July 13-17 2026Graph Machine Learning
28 февр., 05:49
PhD Position in Graph Learning at the University of Vienna, AustriaA PhD student position is available within the Machine Learning with Graphs group at the Faculty of Computer Science, University of Vienna. We are looking for a highly motivated applicant with a solid background and strong interest in machine learning, graph theory, and their mathematical foundations to join our team. The successful candidate will pursue research in the broad area of graph machine learning and may address both theoretical and practical questions.More information on the position and the application process is available at the job portal of the University of Vienna: https://jobs.univie.ac.at/job/University-assistant-predoctoral-PhD-Position-in-Graph-Learning/1368058133/Application deadline: 26.3.2026Graph Machine Learning
16 февр., 14:22изменён
Uni Leipzig looking for a motivated student for a PhD position in Graph Machine Learning at Leipzig University. We will mostly be working on generating graphs that come with 3D information such as neurons and biological trees. More information and the application form are here: https://uni-leipzig.talentstorm.de/stellenangebote/25463uni-leipzig.talentstorm.deStellenangebote - Jetzt online bewerbenGraph Machine Learning
2 окт. 2025 г., 04:46изменён
Tired of evaluating your graph ML models on Cora, CiteSeer, and PubMed? We have a better benchmark for you! (by Oleg Platonov)Paper: link (NeurIPS 2025 D&B track) Datasets: Zenodo and PyG (in PyG, all the necessary feature preprocessing can be done automatically) Code: GitHubRecently, there has been a lot of criticism of existing popular graph ML benchmark datasets concerning such aspects as lacking practical relevance, low structural diversity that leaves most of the possible graph structure space not represented, low application domain diversity, graph structure not being beneficial for the considered tasks, and potential bugs in the data collection processes. Some of these criticisms previously appeared on this channel.To provide the community with better benchmarks, we present GraphLand: a collection of 14 graph datasets for node property prediction coming from diversearXiv.orgGraphLand: Evaluating Graph Machine Learning Models on Diverse...Although data that can be naturally represented as graphs is widespread in real-world applications across diverse industries, popular graph ML benchmarks for node property prediction only cover a...Graph Machine Learning
2 окт. 2025 г., 04:45
How can we create general-purpose graph foundation models? (by Dmitry Eremeev)For a long time, we believed that general-purpose graph foundation models were impossible to create. Indeed, graphs are used to represent data across many different domains, and thus graph machine learning must handle tasks on extremely diverse datasets, such as social, information, transportation, and co-purchasing networks, or models of various physical, biological, or engineering systems. Given the vast differences in structure, features, and labels among these datasets, it seemed unlikely that a single model could achieve robust cross-domain generalization and perform well on all of them.However, we noticed that tabular machine learning faces a similar challenge of working with diverse datasets containing different features and labels. And yet, this field has recently witnessed the emergence of firstGraph Machine Learning
21 сент. 2025 г., 00:40
GraphML News (September 2025) - Stanford Graph Learning WS, MoML, RF Diffusion 3While the community is processing NeurIPS rejects due to “limited physical space” and rushing to the ICLR deadline, it’s about time to plan attending some future events!🌲 Stanford organizes its annual Graph Learning Workshop on Oct 14th. The main topics are Relational Foundation Models (get ready to hear a lot about it, hehe), Agents (Biomni is quite successful), and fast LLM inference. I attended the event last 3 years and it was quite fun.🧬 About one week later (Oct 22nd) and on the East Coast, MIT organizes Molecular ML (MoML) conference going full Geometric DL mode — expect news about Boltz and new drug discovery methods, most of the big pharma is in the sponsors.🧬🧬 The Baker Lab released a pre-print of RFDiffusion 3 (the data pipeline of it, AtomWorks, was pre-printed a bit earlier). ComparedGraph Machine Learning
30 авг. 2025 г., 05:45
GraphML News (Aug 30th) - OpenAI enters bio, AtomWorks, OrbMol, NeurIPS workshops📈 The church of scale enters comp bio: OpenAI published first results on protein design of Yamanaka factors (linked to cell aging) together with Retro Bio (where sama happens to be one of investors). The backbone is gpt-4b micro initialized from an existing 4o checkpoint and enriched with “tokenized 3D structure data” (remember ESM-3?) fine-tuned on a specialized dataset. Experimental results are claimed to be quite solid: hit rates of 30-50% (typically it’s less than 10%) with a bunch of other biochemistry markers. The argument between scalable non-equivariant models vs bespoke geometric models got a new data point: will raw compute of OpenAI + vanilla transformers conquer the biotech world too? We’ll keep you posted.🧬 BakerLab released RosettaFold 3 and AtomWorks, a data processing framework used toOpenAIAccelerating life sciences researchDiscover how a specialized AI model, GPT-4b micro, helped OpenAI and Retro Bio engineer more effective proteins for stem cell therapy and longevity research.Graph Machine Learning
9 авг. 2025 г., 04:41
GraphML News (Aug 9th) - AITHYRA Call for PhD students, Chai Discovery Round, Graph Learning Meets Theoretical CSWhile everyone is busy with GPT-5, Opus 4.1, and GPT-OSS, let’s sneak in some graph news!🎓 A few days ago you could’ve seen an AITHYRA call for postdocs - but fear not if you are still deciding about starting your scientific career, AITHYRA has a call for PhD students too! The plan includes 15-20 fully funded scholarships on the intersection of AI/ML, Molecular Technologies and Systems Medicine (degree either from Medical University or TU of Vienna). Application deadline is September 10, 2025. Glad to see Vienna becoming a new scientific hub in Europe.💸 Chai Discovery raised $70M Series A from Menlo Ventures & Anthology Fund (Anthropic), Thrive Capital, OpenAI + others ($30M seed). The startup is known for Chai-2 generative model and aims at antibody design. CongratsGraph Machine Learning
3 авг. 2025 г., 16:33
Postdoctoral Researcher Position in Geometric Deep Learning & AI for Science at AITHYRAb/w AITHYRA and Technical University of ViennaMichael Bronstein, AITHYRA Scientific Director AI and Honorary Professor of the Technical University of Vienna in collaboration with Ismail Ilkan Ceylan, expert in graph machine learning, invites outstanding candidates to apply for a postdoctoral research position in Geometric Deep Learning, with a strong emphasis on applications to biology and scientific discovery. This unique research collaboration between AITHYRA and the Technical University of Vienna offers an exceptional opportunity to engage in both foundational machine learning research and high-impact interdisciplinary applications in the natural sciences. The position offers access to top-tier academic and industry research ecosystems and is ideally suited for researchers seeking to push theaithyra.onlyfy.jobsApplication ProcessApply nowGraph Machine Learning
3 авг. 2025 г., 03:38
GraphML News (Aug 3rd) - Graph Foundation Models from Google, PyG ecosystem expandingIt’s been a while since the last post, let’s catch up with the news!🔮 ICML brought a handful of announcements, eg, our team at Google published a blog post on the in-house Graph Foundation Model which particularly excels on relational data and brings nice (3-40x) benefits compared to SOTA tabular models. It’s quite astounding that the tabular ML world has been overlooking graph modeling for this kind of data for many years leaving lots of performance on table. Well, as we said last year, GFMs are already here and will continue to improve across all axes, from systems and infra to modeling and better generalization.🌟 Besides that, ICML published a list of outstanding paper awards and a handful of them do use graph learning in one way or another - this is an excellent reminder that beating oldGoogle ResearchGraph foundation models for relational dataTreating relational tables as interconnected graphs powered by advances in graph learning enables training foundational models that generalize to arbitrary tables, features, and tasks.Graph Machine Learning
4 июл. 2025 г., 03:43
GraphML News (July 4th 🦅) - Chai-2, SAIR dataset, UMA 1.1, Why flow matching generalizesSome quick news before the BBQ time and beating aliens over NYC.🧬 Chai Discovery announced Chai-2 that excels at antibody design generating novel ones for 50+ protein targets achieving 16% binding rate in wet lab tests (that’s quite a lot). The tech report says the backbone is a modified Chai-1 but probably with lot more new training data (which is a good sign, it’s 2025 and models don’t matter, data does). Chai-2 is announced just 2 weeks after Boltz-2 - both started as AlphaFold3 reproductions but now moving in slightly different directions, eg, Chai-2 is not open-source anymore. We’ll be keeping an eye on their successes.🧬 🧬 SandboxAQ released a new SAIR dataset (structurally augmented IC50 repository) comprised of 5M structures over 1M+ unique protein-ligand systems (folded withGraph Machine Learning
21 июн. 2025 г., 17:14
GraphML News (June 21st) - Skala, Temporal RDL, Future of Graph Learning, Erwin⚛️ MSR AI 4 Science announced Skala - an exchange-correlation (XC) ML potential to estimate chemical properties of molecules (energy and force fields). Skala represents molecules via density features obtained from meta-generalized-gradient approximation (meta-GGA) and is practically an irregular integration grid. The main model employs radial functions and spherical harmonics to capture non-local interactions and run integration over space. Skala was trained on a new dataset of 150k data points and reaches SOTA MAE on the W4-17 dataset. Preprint and data are available (lots of fancy equations in the appendix).🕸️ Kumo published an interesting piece on temporal dependencies in relational DL where features change over time - note that in RelBench edges have timestamps but features are static. They triedMicrosoft ResearchUsing deep learning to increase the accuracy of computational chemistry and density functional theoryMicrosoft researchers achieved a breakthrough in the accuracy of DFT, a method for predicting the properties of molecules and materials, by using deep learning. This work can lead to better batteries, green fertilizers, precision drug discovery, and more.Graph Machine Learning
14 июн. 2025 г., 18:12
GraphML News (June 14th) - Boltz-2, OpenBind, Musings on equivarianceBack to the normal schedule!🧬 The biggest announcement of the week - MIT and Recursion released Boltz-2, perhaps the most successful open-source reproduction of AlphaFold 3. v2 brings binding affinity prediction (orders of magnitude faster than physics simulations), model improvements and inference speedups. The preprint also report an experiment combining Boltz with SynflowNet to generate binders for the TYK2 protein. Code and model weights are already available.🇬🇧 UK announced the OpenBind initiative aiming to collect data for 500k protein-ligand complexes using X-ray crystallography and synchrotron facilities at Diamond Light Source. The academic side includes all the big names you’d expect - Charlotte Deane, Frank von Delft, David Baker - as well as the industrial part which include Isomorphic Labs, Roche,Graph Machine Learning
25 мая 2025 г., 02:05
GraphML News (May 14th) - KumoRFM, Open Molecules 2025, TxPertLots of news over the past two weeks other than new Gemini and Claude models!🏆 KumoAI presented KumoRFM - the first graph foundation model for relational databases capable of zero-shotting node regression, node classification, and link prediction. Given any set of relational tables with any categorical or numerical features and transforming them into a graph, you can now zero-shot typical tasks like regression or classification. Perhaps the biggest difference of KumoRFM compared to other inductive models is using in-context learning, that is, for each prediction task we’d mine not only an ego-graph around the target entity, but also ego-graphs about relevant nodes with similar labels. The backbone for encoding ego-graphs for node-related tasks is the Relational Graph Transformer (another new pre-print), then graph vectorsGraph Machine Learning
10 мая 2025 г., 03:12
GraphML News (May 10th) - PageRank and New Pope, Scientific Agents, more blogs🤌 🇻🇦 Researchers from Bocconi University in Milan rolled the best usage of network science of 2025: using centrality measures to predict the results of the conclave (who elects the next Pope). They mined a graph of Vatican cardinals according to their job duties, informal relationships, and “spiritual genealogies”, and computed a bunch of centrality measures - eigenvector centrality (probably a PageRank), betweenness centrality (affordable for small networks), and some clustering metrics. One of them did rank the real elected Pope in the top (although others didn’t have him in top-5) which is a cool result. Good ole PageRank still makes headlines in 2025!🦅 FutureHouse announced the Platform for scientific discovery tasks. Practically, the Platform combines 4 distinct multimodal agents (avian beings):Graph Machine Learning
2 мая 2025 г., 16:23
Graph Learning Will Lose Relevance Due To Poor Benchmarksby Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, Luis Müller, Jan Tönshoff, Antoine Siraudin, Viktor Zaverkin, Michael M. Bronstein, Mathias Niepert, Bryan Perozzi, Mikhail Galkin, Christopher Morris📜 arxiv📣 Our new spicy ICML 2025 position paper. Graph learning is less trendy in the ML world than it was in 2020-2022. We believe the problem is in poor benchmarks that hold the field back - and suggest ways to fix it!We identified three problems: #️⃣ P1: No transformative real-world applications - while LLMs and geometric generative models become more powerful and solve complex tasks every generation (from reasoning to protein folding), how transformative could a GNN on Cora or OGB be?P1 Remedies: The community is overlooking many significant and transformative applications, including chip design and broaderarXiv.orgPosition: Graph Learning Will Lose Relevance Due To Poor BenchmarksWhile machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and relevance. Current...Graph Machine Learning
13 апр. 2025 г., 03:31
GraphML News (April 13th) - Orb V3, RF Diffusion 2, Breakthrough Prizes, ICML 2025 Workshops🔮 Orbital Materials released Orb V3, the next version of the universal ML potential. Some improvements include training a wider but shallower model (5-layer MPNN with 1024d MLP instead of 15-layer with 512d in v2), having both versions where forces are predicted directly (non-conservative) or as a gradient of energy (conservative force field), and a good bunch of training tricks listed on github. ORB v3 shows top results on MatBench Discovery and now has a confidence prediction head akin to pLDDT in AlphaFold. The accompanying paper and model checkpoint are available, plug them in right away.🧬 The Baker Lab released RF Diffusion 2 (as a pre-print right now) focusing on de novo enzyme design. RFD2 is a Riemannian flow matching model in both frame and coordinate space (the frame part is veryGraph Machine Learning
5 апр. 2025 г., 05:32
GraphML News (April 5th) - Isomorphic Round, Graph Transformers at Kumo, new blogsGot some news!💸 Isomorphic Labs raised a generous $600M from Thrive Capital, GV, and Alphabet in the first external round. The attached press release also mentions collaborations with pharma giants Eli Lilly and Novartis - seems like whatever comes next after AlphaFold 3 looks quite appealing to the industry. We’ll keep you posted in our Geometric Wall Street Bulletin.🏵️ Looking at LLM guts from the graph learning perspective becomes popular: Anthropic posted a massive study in two papers and lots of visual material on AI biology with strong graph vibes - LLMs perform multi-hop reasoning with concept graphs in mind, and you can actually identify circuits (DAGs) of activations doing certain kind of computation.🚚 Kumo published a nice blog post on using graph transformers at scale in relational DLGraph Machine Learning
23 мар. 2025 г., 04:05
GraphML News (March 23rd) - Neo-1 and Lila Sciences round🧬 VantAI announced Neo-1, a foundation model for structure prediction and de novo generation capable of doing a bunch of protein design tasks (folding, co-folding, docking, all-atom molecule design, fragment linking, and more) at once instead of different modules. While we are waiting for the tech report, we could guesstimate that Neo-1 is an all-atom latent generative model (perhaps a Diffusion Transformer like in other competitors as it’s powered by a hefty cluster of H100s) with some advanced sampling techniques beyond standard guidance - the blog post talks about optimizing for non-differentiable properties with reward-like models and it sounds quite similar to the ICLR 2025 paper on posterior prediction.As impressive as the modeling advances are, true aficionados know that data diversity and distribution is even moreGraph Machine Learning
16 мар. 2025 г., 00:24
GraphML News (March 16th) - ICLR 2025 Workshops, Mediterranean Summer School🍻 ICLR 2025 is approaching and it’s time to select some workshops to attend to chat with friends and hide from the heat of Singapore. Graph learning aficionados might be interested in a various bio / health / science workshops:- Neural Network Weights as a New Data Modality - GemBio - ML for Genomics - Agentic AI 4 Science - AI for Nucleic Acids - Learning Meaningful Representations of Life (LMRL) - AI 4 Material Discovery - Frontiers in Probabilistic Inference: learning meets SamplingSome of them have already published the accepted papers on OpenReview - here is a usual reminder to go find some hidden gems as most workshop papers evolve into full conference papers.🇭🇷 The Balkans get all the fancy machine learning summer schools in 2025: we know that EEML 2025 will take place in Sarajevo, July 21-26. If
