18 accepted papers
We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted logarithmic pooling that strictly improves every member's welfare. …
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 extracted by steerable convolutions. Operating in Fourier space,…
Several recent papers have proposed increasing the expressiveness of graph neural networks by exploiting subgraphs or other topological structures. In parallel, researchers have investigated higher order permutation equivariant networks. In this paper we tie these two threads together by providing a…
Recent works have shown that extending the message passing paradigm to subgraphs communicating with other subgraphs, especially via higher order messages, can boost the expressivity of graph neural networks. In such architectures, to faithfully account for local structure such as cycles, the local o…
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 have been particularly notable in graph reconstructio…
Recent work on permutation equivariant neural networks has mostly focused on the first order case (sets) and second order case (graphs). We describe the machinery for generalizing permutation equivariance to arbitrary $k$-ary interactions between entities for any value of $k$. We demonstrate the eff…
Computational methods that operate on three-dimensional (3D) molecular structure have the potential to solve important problems in biology and chemistry. Deep neural networks have gained significant attention, but their widespread adoption in the biomolecular domain has been limited by a lack of eit…
We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and apply local convolutions that are equivariant to each subgraph's automorphism group. Specific choices of local neighborho…
Traditionally, permutation puzzles such as the Rubik’s Cube were often solved by heuristic search like $A^*\!$-search and value based reinforcement learning methods. Both heuristic search and Q-learning approaches to solving these puzzles can be reduced to learning a heuristic/value function to deci…
We present a neural network architecture that is fully equivariant with respect to transformations under the Lorentz group, a fundamental symmetry of space and time in physics. The architecture is based on the theory of the finite-dimensional representations of the Lorentz group and the equivariant…
We propose Cormorant, a rotationally covariant neural network architecture for learning the behavior and properties of complex many-body physical systems. We apply these networks to molecular systems with two goals: learning atomic potential energy surfaces for use in Molecular Dynamics simulations,…
Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In this paper we propose a generalization of this work that generally exhibits improved pe…
Most existing neural networks for learning graphs deal with the issue of permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors. We argue that this imposes a limitation on their representation power, and ins…
Convolutional neural networks have been extremely successful in the image recognition domain because they ensure equivariance with respect to translations. There have been many recent attempts to generalize this framework to other domains, including graphs and data lying on manifolds. In this paper…
Gaussian process regression generally does not scale to beyond a few thousands data points without applying some sort of kernel approximation method. Most approximations focus on the high eigenvalue part of the spectrum of the kernel matrix, $K$, which leads to bad performance when the length scale…
Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric matrices -- an important aspect in the success of many vision…
Multiresolution Matrix Factorization (MMF) is a recently introduced method for finding multiscale structure and defining wavelets on graphs and matrices. MMF can also be used for matrix compression (sketching). However, the original MMF algorithm of (Kondor et al., 2014) scales with n^3 or worse (wh…
Many real world graphs, such as the graphs of molecules, exhibit structure at multiple different scales, but most existing kernels between graphs are either purely local or purely global in character. In contrast, by building a hierarchy of nested subgraphs, the Multiscale Laplacian Graph kernels (M…