Emanuele Rodolà

TL;DR: In this article, a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features is proposed.

TL;DR: This paper proposes a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features and test the proposed method on standard tasks from the realms of image-, graph-and 3D shape analysis and show that it consistently outperforms previous approaches.

TL;DR: MaSIF (molecular surface interaction fingerprinting) is presented, a conceptual framework based on a geometric deep learning method to capture fingerprints that are important for specific biomolecular interactions that will lead to improvements in the understanding of protein function and design.

TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.

TL;DR: Anisotropic convolutional neural networks (ACNN) as discussed by the authors is a generalization of classical CNNs to non-Euclidean domains, where classical convolutions are replaced by projections over a set of oriented anisotropic diffusion kernels.