Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Kondor, Risi"'
Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well suited to modeling certain types of graphs with complex multiscale or hi
Externí odkaz:
http://arxiv.org/abs/2406.00469
Autor:
Kundu, Soumyabrata, Kondor, Risi
In this work we introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group $\mathrm{SE}(d)$. We propose an equivariant attention mechanism that operates on features ex
Externí odkaz:
http://arxiv.org/abs/2405.15932
Inner product-based decoders are among the most influential frameworks used to extract meaningful data from latent embeddings. However, such decoders have shown limitations in representation capacity in numerous works within the literature, which hav
Externí odkaz:
http://arxiv.org/abs/2402.06662
Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to computational challeng
Externí odkaz:
http://arxiv.org/abs/2310.01704
Several recent papers have recently shown that higher order graph neural networks can achieve better accuracy than their standard message passing counterparts, especially on highly structured graphs such as molecules. These models typically work by c
Externí odkaz:
http://arxiv.org/abs/2306.10767
Latent representations of drugs and their targets produced by contemporary graph autoencoder models have proved useful in predicting many types of node-pair interactions on large networks, including drug-drug, drug-target, and target-target interacti
Externí odkaz:
http://arxiv.org/abs/2302.08680
Contemporary graph learning algorithms are not well-defined for large molecules since they do not consider the hierarchical interactions among the atoms, which are essential to determine the molecular properties of macromolecules. In this work, we pr
Externí odkaz:
http://arxiv.org/abs/2302.08647
Spatio-temporal signals forecasting plays an important role in numerous domains, especially in neuroscience and transportation. The task is challenging due to the highly intricate spatial structure, as well as the non-linear temporal dynamics of the
Externí odkaz:
http://arxiv.org/abs/2302.08643
Publikováno v:
Mach. Learn.: Sci. Technol. 5 025044, 2024
Many learning tasks, including learning potential energy surfaces from ab initio calculations, involve global spatial symmetries and permutational symmetry between atoms or general particles. Equivariant graph neural networks are a standard approach
Externí odkaz:
http://arxiv.org/abs/2211.07482
Latent representations of drugs and their targets produced by contemporary graph autoencoder-based models have proved useful in predicting many types of node-pair interactions on large networks, including drug-drug, drug-target, and target-target int
Externí odkaz:
http://arxiv.org/abs/2209.09941