Is Denoising Diffusion all you need? — The breakthrough in Denoising Diffusion Probabilistic Models (DDPM) happened about 2 years ago. Since then, we observe dramatic improvements in generation tasks: GLIDE, DALL-E 2, Imagen, Stable Diffusion for images, Diffusion-LM in language modeling, diffusion for video sequences, and even diffusion for reinforcement learning. Diffusion might be the biggest trend…

Recent advancements and hot trends, July 2022 edition — International Conference on Machine Learning (ICML) is one of the premier venues where researchers publish their best work. ICML 2022 was packed with hundreds of papers and numerous workshops dedicated to graphs. We share the overview of the hottest research areas 🔥 in Graph ML. This post was written by…

Recipes for cooking the best graph transformers — In 2021, graph transformers (GT) won recent molecular property prediction challenges thanks to alleviating many issues pertaining to vanilla message passing GNNs. Here, we try to organize numerous freshly developed GT models into a single GraphGPS framework to enable general, powerful, and scalable graph transformers with linear complexity for all…

Starting a new Inductive Link Prediction Challenge 2022 — Since very 2011, the area of representation learning over Knowledge Graphs has been dominated by one task: transductive link prediction. Is it still relevant in 2022? 🤔 Rather not. In the transductive setup (🖼 ☝️) we perform inference (our link prediction) over the same graph seen at training time. We…

Hot trends and major advancements — It’s been quite a year for Graph ML — thousands of papers, numerous conferences and workshops… How do we catch up with so many cool things happening around? Well, we are puzzled as well and decided to present a structured look at Graph ML highlighting 🔥 trends and major advancements. …

Your regular digest of KG research, November edition — I didn’t make it to Punta Cana this year 😢 but I’m happy (remotely) for the folks who managed to get there in spite of all traveling restrictions! Premium content inside 🏖 The autumn got very busy and I’d like to try a shorter format: each big topic has one…

Your guide to the KG-related NLP research, ACL edition — Welcome to the third iteration of our regular overview of NLP papers around Knowledge Graphs, this time published at ACL 2021! What will be (or has been) trending this year that you wouldn’t want to miss? 👀 ACL’21 remains to be one of the largest NLP venues: 700+ full papers…

Mapping each node to an embedding vector results in enormously large embedding matrices. Is there a way to have a fixed-size vocabulary of tokens akin to “subword units”? — This blog post was co-authored with Etienne Denis and Paul Wu and is based on our paper “NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs”. Knowledge graphs (KGs) keep growing larger and larger: Wikidata has about 100M nodes (entities), YAGO 4 is about 50M nodes, and custom graphs like…

Your guide to the KG-related research in ML, May edition — ICLR has recently surpassed other AI venues in terms of attracted citations and general appraisal in the community 🎉 Let’s check out recent goodies in our favorite knowledge graphs domain! First, I would like to mention other great summaries of ICLR and other graph-related papers by fellow colleagues 👏: Sergey…