Paper defines mathematical framework for neural network explainability.
problem Neural network explainability and equivariant operators.
method Mathematical framework based on Group Equivariant Non-Expansive Operators (GENEOs) and complexity measures.
result Formal properties and interpretability of Group Equivariant Operators (GEOs) defined.
Frame Averaging makes neural networks invariant or equivariant to new symmetries.
problem Designing neural networks that respect symmetries while being expressive and efficient.
method Introduces Frame Averaging (FA) as a systematic framework to adapt architectures to become invariant or equivariant to new symmetries.
result Frame Averaging guarantees exact invariance or equivariance while being simpler to compute than full group averaging.
New neural network processes 3D volumes with improved equivariance.
problem Improving neural network performance on 3D volumes with symmetries.
method Equivariant neural network using moving frames approach.
result Trained model outperforms benchmarks in medical volume classification.
New equivariant filters improve graph classification.
problem Designing deep learning models for graph symmetries.
method Nonlinear spectral filters (NLSFs) that are equivariant to graph functional shifts.
result NLSFs outperform existing spectral GNNs in graph classification.
The paper generalizes equivariant neural networks on homogeneous spaces to the non-linear setting.
problem Equivariant neural networks on homogeneous spaces.
method Deriving generalized steerability constraints for non-linear equivariant layers.
result The universality of the derived construction for non-linear equivariant layers.
The aim of this paper is to provide a general mathematical framework for group equivariance in the machine learning context. The framework builds on a synergy between persistent homology and the theory of group actions. We define group-equivariant non-expansive operators (GENEOs), which are maps between function spaces…
The study quantifies how many objects can be linearly classified under all views.
problem Understanding the expressivity of group-equivariant representations.
method Generalization of Cover's Function Counting Theorem to quantify separable dichotomies.
result The fraction of separable dichotomies is determined by the fixed space dimension of the group action.
Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
problem Equivariance in deep learning for arbitrary transformations, especially in physics.
method Introduces SE(3) equivariant graph neural networks with complete local frames to efficiently approximate geometric quantities.
result Achieves best or competitive performance in Newton mechanics modeling and equilibrium molecule conformation generation.
BI-EqNO improves Bayesian inference with flexible neural operators.
problem Inaccurate estimation of marginal likelihoods in approximate Bayesian methods.
method Equivariant neural operator framework for generalized approximate Bayesian inference.
result BI-EqNO enhances both deterministic and stochastic approaches to Bayesian inference.
New methods improve translation-equivariant neural processes for modeling unknown functions.
problem Modeling unknown latent functions from irregularly sampled measurements.
method Volterra series and set Fourier convolutions to address translation-equivariance and efficiency.
result Improved translation-equivariant neural processes with analytical transparency and linear scalability.
Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we …
Proposes a topological model for partial equivariance in neural networks.
problem Capturing partial equivariance in neural networks for data analysis.
method Introduces P-GENEOs and studies spaces of measurements and P-GENEOs between them.
result Spaces of measurements and P-GENEOs have convenient approximation and convexity properties.
The paper studies geometric properties of group equivariant operators and their Riemannian structure.
problem Understanding the geometric structure of group equivariant operators.
method Endowing the space of group equivariant non-expansive operators with a Riemannian manifold structure and using gradient descent methods.
result Gradient descent methods can be applied to minimize cost functions on the space of group equivariant non-expansive operators.
Group-equivariant subsampling layers improve CNNs' equivariance.
problem Non-translation equivariance in subsampling operations.
method Translation and group-equivariant subsampling/upsampling layers.
result Group-equivariant autoencoders learn equivariant representations.
HKConv learns hyperbolic features by aggregating kernel points.
problem Challenges in learning good hyperbolic representations using Euclidean operations.
method Proposes HKConv, a trainable hyperbolic convolution that correlates local features with kernel points and aggregates them.
result HKConv learns expressive local features according to hyperbolic geometry and enjoys equivariance to permutation and invariance to parallel transport.
SpeqNets improve graph neural networks by scaling and adapting to graph sparsity.
problem Graph neural networks struggle with permutation-equivariant functions and scalability to large graphs.
method Introducing sparsity-aware, permutation-equivariant graph networks with heuristics for graph isomorphism.
result Significantly improved predictive performance and reduced computation times compared to existing methods.
Homotopy operators help describe structures in equivariant deformation problems.
problem Equivariant deformation problems in algebraic structures.
method Use homotopy operators for an L∞-algebra associated with the problem. result Smooth parametrization of the space of structures around a given one.
New framework uses symmetry-based matrices for efficient, flexible NNs.
problem Designing neural networks with relaxed equivariance.
method Symmetry-based structured matrices, Group Matrices (GMs).
result GMs enable competitive performance with fewer parameters.
We formulate, for any Lie group G acting isometrically on a manifold M, the general notion of a G-equivariant elliptic operator that is invertible outside of a G-cocompact subset of M. We prove a version of the Rellich lemma for this setting and use this to define the equivariant index of such operators. We show that G…
We present a version of the equivariant gradient degree defined for equivariant gradient perturbations of an equivariant unbounded self-adjoint operator with purely discrete spectrum in Hilbert space. Two possible applications are discussed.
GNNs generalize CNNs for graph data, showing equivariance and stability.
problem Processing signals on graphs.
method Graph convolutional filters, nonlinearities, stacked layers.
result GNNs converge to graphon neural networks under graph convergence.
Unified understanding of neural networks on group operations verified.
problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.
We introduce a new class of natural, explicitly defined, transversally elliptic differential operators over manifolds with compact group actions. Under certain assumptions, the symbols of these operators generate all the possible values of the equivariant index. We also show that the components of the representation-va…
In this paper, we compute the first two equivariant heat kernel coefficients of the Bochner Laplacian on differential forms. The first two equivariant heat kernel coefficients of the Bochner Laplacian with torsion are also given. We also study the equivariant heat kernel coefficients of nonmininmal operators on differe…
We use contact geometry to describe the monoid of projectively equivariant meromorphic differential operators on a complex curve, quantization of which generalizes known constructions of classical equivariants to non-commutative function algebras in several variables.
Paper presents a novel hyperbolic neural network for efficient data representation.
problem Efficient representation of hierarchical data in hyperbolic space.
method Develops a fully hyperbolic neural network using projections and equivariant embeddings.
result Proves the proposed embedding is isometric and equivariant under Lorentz transformations.
Study of invariants on manifolds with boundary involving equivariant spectral flow and η-invariants.
problem Equivariant invariants on manifolds with boundary.
method Analysis of Dirac operators, winding numbers, spectral flow, Maslov indices, and η-invariants.
result Established relation between equivariant η-invariants and Maslov triple indices.
In this paper, we prove a local equivariant index theorem for sub-signature operators which generalizes the Zhang's index theorem for sub-signature operators.
We prove inverse spectral results for differential operators on manifolds and orbifolds invariant under a torus action. These inverse spectral results involve the asymptotic equivariant spectrum, which is the spectrum itself together with "very large" weights of the torus action on eigenspaces. More precisely, we show …
Equivariant neural networks use symmetry to interpret complex data.
problem Interpreting and understanding the behavior of equivariant neural networks.
method Decompose layers into simple representations and analyze nonlinear activation functions.
result Equivariant neural networks can be interpreted using a filtration generalizing Fourier series.
Constructs equivariant spectral flow for Dirac-type operators on manifolds.
problem Calculating spectral flow for Dirac-type operators on manifolds with group actions.
method Equivariant spectral flow construction for paths of Dirac-type operators on manifolds.
result Relates delocalised η-invariants and ρ-invariants for different positive scalar curvature metrics.
ChebLieNet uses Lie groups to create invariant spectral graph networks.
problem Handling anisotropic data in graph neural networks.
method Develops anisotropic convolutional layers on Lie groups with Riemannian metrics.
result Demonstrates the effectiveness of balancing equivariance and invariance.
Using equivariant Toeplitz operator calculus, we give a new proof of the Atiyah-Weinstein conjecture on the index of Fourier integral operators and the relative index of CR structures.
In this paper, we give a geometric expression for the multiplicities of the equivariant index of a spin-c Dirac operator.
Improved set prediction model using multiset-equivariant operations and approximate implicit differentiation.
problem Existing set prediction models struggle with multisets and cannot represent certain functions.
method Introduced multiset-equivariance, improved DSPN with approximate implicit differentiation, and applied to CLEVR object property prediction.
result Significantly improved object property prediction on CLEVR dataset.
In this note the fractional analytic index, for a projective elliptic operator associated to an Azumaya bundle, of DG/0402329 is related to the equivariant index of Atiyah and Singer for an associated transversally elliptic operator.
A universal collection of 4 invariants improves neural network accuracy for molecular dynamics.
problem Improving accuracy of neural networks in molecular dynamics.
method Developed a universal collection of 4 smooth scalar invariants on M(3) x M(3) and evaluated their effectiveness in a PONITA neural network architecture.
result Using a universal collection of invariants significantly improves neural network accuracy.
Lie groupoid equivariant neural networks are a new type of neural network.
problem Designing neural networks that respect the structure of Lie groupoids.
method Introducing Lie groupoid equivariant convolutions and layers, and showing their equivalence to Lie algebroid-equivariant networks.
result Lie groupoid equivariant neural networks are equivalent to certain Lie algebroid-equivariant networks.
In this note, we give a geometric expression for the multiplicities of the equivariant index of a Dirac operator twisted by a line bundle.
New method generates equilibrium glass configurations efficiently.
problem Sampling equilibrium configurations of amorphous materials is slow and difficult.
method Riemannian stochastic interpolation framework combining Riemannian stochastic interpolant and equivariant flow matching.
result Enforcing geometric and symmetry constraints significantly improves generative performance.
Characterizes a specific type of neural network for alternating group equivariance.
problem Understanding and characterizing neural networks with alternating group equivariance.
method Characterization of all possible An-equivariant neural networks using tensor powers of Rn. result Found a basis of matrices for learnable, linear An-equivariant layer functions. Formula for index in Lorentzian spacetimes.
problem Developing an index formula for spacetimes with boundary.
method Reduction from equivariant to non-equivariant, Lorentzian spectral flow.
result Equivalence of equivariant index and spectral flow in Lorentzian spacetimes.
Researchers prove an equivariant index theorem on Euclidean space.
problem Calculating the equivariant index of the Bott-Dirac operator on R2n. method Continuous field of C∗-algebras and equivariant index theorem. result Explicit calculation of the equivariant index of the Bott-Dirac operator on R2n. Researchers compute the index of a specific operator on contact manifolds.
problem Computing the index of a twisted Dolbeault operator on toric contact manifolds.
method Using equivariant techniques, they localized the symbol to Reeb orbits and applied polytope decomposition.
result They derived an Atiyah-Bott-Lefschetz type formula for the index.
Paper uses algebraic methods to prove an equivariant Poincaré-Hopf theorem.
problem Equivariant index theory on manifolds.
method Localization algebras and Witten deformation techniques in K-homology.
result Established an equivariant version of the Poincaré-Hopf theorem.
Geometric models improve feature extraction and equivariance in image generation.
problem Improving feature extraction at multiscale levels and reducing network complexity.
method Proposes a geometric generative model based on morphological PDEs and GANs, incorporating equivariance for geometric interpretability.
result Preliminary results show GM-GAN outperforms classical GANs on MNIST data.
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
Explains equivariant neural networks for machine learning.
problem Understanding equivariance in neural networks.
method Simple mathematical treatment of neural network concepts.
result Clarifies the mathematical basis of equivariant neural networks.