1/ When do people need an explanation from an AI system? What makes them trust the answer? Excited to share. jmir.org/2021/11/e29386/ #ExplainableAI #XAI #healthtech with Brent Mittelstadt @bmittelstadt.bsky.social Dan Busbridge & Grant Blank Spoiler: AI should communicate with humans like they're... human.

After a hiatus, a new series of blogs posts. Do differential geometry and algebraic topology sound too exotic for ML? In recent works, we show that tools from these fields bring a new perspective on graph neural networks First post in the series: towardsdatascience.com/graph-neural-n…

We introduce Feature Propagation (FP), a new method to learn on graphs with partially missing node features. With 99% of features missing, FP loses only 4% rel. acc. compared to when all features are available. Bonus: It scales to graphs with >100M nodes arxiv.org/abs/2111.12128

1/4 Hope to see friends new & old tomorrow 4:30pm GMT / 8:30am PT poster session 6 #NeurIPS2021 James Rowbottom Francesco Di Giovanni and I will occupy the prime virtual real estate known as Spot E3 with BLEND neurips.cc/virtual/2021/p…

While most GNNs assume a full set of features for all nodes, real-world graphs often have partially missing node features. In a new blog post with Michael Bronstein, we discuss how we can learn on such graphs using Feature Propagation (10 min read) 📝 towardsdatascience.com/learning-on-gr…

New post Towards Data Science about physics-inspired "continuous" graph ML models 🧵 bit.ly/3pxxx7q

This new partnership will create exciting opportunities for our researchers to collaborate with @twittereng researchers on the development of responsible, community-driven machine learning systems. mila.quebec/en/twitter-ann…

Here it is: the first Learning on Graphs Conference! 🎊 We think this new venue will be valuable for the Graph/Geometric Machine Learning community. What makes it so important+unique? See our blog post! michael-bronstein.medium.com/announcing-the… 1/6

Airbnb is using our SIGN architecture to compute graph embeddings at scale! They chose SIGN to build a maintainable and effective pipeline producing features resulting in "significant gains" in their downstream models. More from Airbnb Engineering : medium.com/airbnb-enginee…

Airbnb is using our SIGN method in production to compute graph-based user embeddings, leading to "notable performance gains". Why was it chosen? Scalability, simplicity and predictive performance. medium.com/airbnb-enginee… Airbnb Engineering

We have two papers accepted at #NeurIPS2022 on neural sheaf diffusion and subgraph GNNs Congratulations to amazing coauthors Francesco Di Giovanni Cristian Bodnar @b_p_chamberlain Pietro Lio' Fabrizio Frasca Haggai Maron Beatrice Bevilacqua

1/4 Today we released two new link prediction models developed over the past 12m. We solve many problems that prevent GNNs succeeding at link prediction by adding a message passing mechanism that uses sketches of subgraphs. arxiv.org/abs/2209.15486

Transparency is important to trust. Birdwatch’s algorithm is publicly available in GitHub, along with all of the data that powers it. Whether you are a researcher, a hobbyist, or just curious, you can run Birdwatch’s algorithm on your own computer: twitter.github.io/birdwatch/rank…

🫡

Tweeps at #NeurIPS2022 #ML4PS2022 @lrml_bio AI for Science looking for exciting jobs in deep learning and molecular sciences? Microsoft Research AI4Science is hiring in Berlin and other sites. DM me or approach my colleagues for more info.

Emanuele Rossi Fabrizio Frasca Francesco Di Giovanni @b_p_chamberlain The best graph ML team attending NeurIPS

Our paper on scaling link prediction to graphs with tens of millions of nodes using subgraph sketching has been awarded an oral presentation (top 5%) at ICLR! arxiv.org/abs/2209.15486 Michael Bronstein Ben Chamberlain Sergey Shirobokov Fabrizio Frasca @[email protected] Nils Hammerla thomas

1/3 Twitter graph ML full house at #ICLR2023 : 📜Poster arxiv.org/abs/2210.00513 🔦Spotlight arxiv.org/abs/2210.01542 top 25% 👄Oral arxiv.org/abs/2209.15486 top 5% spanning my recent interests in continuous GNNs, hyperbolic geometry (applied to RL this time) & link prediction

If you are attending #ICLR2023 come to see our “royal flash”: oral on scalable link prediction, spotlight on hyperbolic RL, and poster on gradient gating in GNNs Ben Chamberlain Konstantin Rusch Edoardo Cetin Emanuele Rossi Fabrizio Frasca thomas @[email protected] Nils Hammerla Sergey Shirobokov