Permutation-equivariant neural networks improve auction mechanisms by reducing regret and sample complexity.
problem Designing optimal auction mechanisms that balance revenue and bidders' regret.
method Introduced permutation-equivariant neural networks to auction mechanisms.
result Permutation-equivariant neural networks decrease expected ex-post regret and improve model generalizability.
Graphs benefit from unique node identifiers but lose permutation-equivariance. We propose a method to maintain this property.
problem Graph Neural Networks' inherent limitations due to message-passing structure.
method Propose permutation-equivariant UID models and a contrastive loss to regularize them.
result Our method improves generalization and convergence, achieving state-of-the-art performance.
New method connects neural networks to diagrammatic algebra.
problem Constructing permutation equivariant neural networks.
method Schur-Weyl duality between symmetric group and partition algebra.
result Simple diagrammatic method for calculating weight matrices.
SMP model preserves proximity and permutation in graph neural networks.
problem Challenges in graph mining, such as community and leader finding.
method Stochastic Message Passing (SMP) model that maintains proximity and permutation-equivariance.
result SMP model effectively preserves node proximities and permutation-equivariance.
Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. Theoretical approaches to the problem have hit some limits in the past decades and analytical solutions are known for only a few simple settings. Computational approaches to the problem through the use of L…
Graph neural networks improve systemic risk measures for financial networks.
problem Computing systemic risk measures for graph-structured financial networks.
method Extended permutation equivariant neural networks (X-PENNs) for numerical approximation.
result Graph neural networks outperform other methods in approximating optimal allocations.
Introduces P-tensors for generalized higher-order message passing in graph neural networks.
problem Expanding the expressive power of graph neural networks through higher-order structures.
method Introduces P-tensors to define the most general form of permutation equivariant message passing.
result Achieves state-of-the-art performance on molecular datasets.
New neural networks respect symmetries in symmetric tensors, improving efficiency and generalization.
problem Learning from symmetric tensors efficiently and respecting their inherent symmetries.
method Developed two characterizations of linear permutation equivariant functions between symmetric power spaces of R^n.
result These functions are highly data efficient compared to standard MLPs and generalize well to different sizes of symmetric tensors.
New basis for permutation equivariant layers reduces computation costs.
problem Efficiently computing permutation equivariant layers in neural networks.
method Generalized partition algebra basis with low-rank tensors.
result Low-rank tensors enable faster computation compared to orbit basis.
Paper presents a novel neural network for MIMO symbol detection.
problem Handling a variable number of users in MIMO systems.
method Recurrent and permutation equivariant neural network architecture with iterative decoding.
result The neural detector outperforms existing methods in accuracy and efficiency.
ExNODE uses ODE to model sets with permutation equivariance.
problem Capturing intra-set dependencies in unordered sets.
method Exchangeable Neural ODE (ExNODE) using ODE.
result ExNODE achieves permutation equivariance for set modeling.
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.
Derives formulae for general permutation equivariant layers and presents a second order graph variational encoder.
problem Tackles the limitation of previous equivariant neural networks by considering permutations of matrices.
method Derives formulae for general permutation equivariant layers, including matrix permutations. Presents a second order graph variational encoder.
result Latent distribution of equivariant generative models must be exchangeable.
Using deep neural networks that are either invariant or equivariant to permutations in order to learn functions on unordered sets has become prevalent. The most popular, basic models are DeepSets [Zaheer et al. 2017] and PointNet [Qi et al. 2017]. While known to be universal for approximating invariant functions, DeepS…
New model preserves symmetry in multivariate time series, improving performance.
problem Implicit ordering in MTS models violates inherent exchangeability.
method Permutation-equivariant 2D state space model with canonical architecture.
result Eliminates sequential dependency chains and simplifies stability analysis.
The paper introduces fixed-point centralities for networks and graphons.
problem Defining network centralities for networks and graphons.
method Fixed-point centralities defined via permutation equivariant mappings and graphons.
result Variation bounds of fixed-point centralities under mild assumptions.
Proposes supervised method for whole DAG causal structure learning.
problem Learning causal directions from data, especially for whole DAG structure.
method Supervised learning approach using permutation equivariant models.
result Promising results compared to previous approaches on synthetic and real data.
Enhances graph neural networks with structural message-passing for better generalization.
problem Limited representation power and inability to learn basic graph topological properties.
method Proposes a framework that includes a one-hot encoding of nodes and parametrized message and update functions ensuring permutation equivariance.
result Achieves state-of-the-art results on molecular graph regression on the ZINC dataset.
Novel neural GP kernels learn stable, flexible covariance structures.
problem Scalable and flexible covariance kernels for Gaussian processes.
method Directly learn kriging coefficients and conditional standard deviations using deep neural architectures exploiting permutation-equivariant structure.
result Improved training stability and data efficiency with expressive, non-stationary kernels.
Improved phylogenetic inference with normalizing flows.
problem Limitations of current diagonal Lognormal branch length approximation in VBPI.
method Proposes VBPI-NF using normalizing flows to handle non-Euclidean branch length space.
result Significantly improves phylogenetic posterior estimation on real data.
Despite the widespread adoption of Transformer models for NLP tasks, the expressive power of these models is not well-understood. In this paper, we establish that Transformer models are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support, which is quite surp…
Neural sorting network improves sorting accuracy for complex inputs.
problem Sorting complex inputs like multi-digit images.
method Differentiable swap function and permutation-equivariant Transformer network.
result Our method outperforms baseline methods on various sorting benchmarks.
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
New neural networks learn graph symmetries.
problem Learning from graph data without considering vertex relations.
method Constructs equivariant neural networks to Aut(G) group.
result Characterizes learnable, linear, Aut(G)-equivariant functions.
Learning generative models for graph-structured data is challenging because graphs are discrete, combinatorial, and the underlying data distribution is invariant to the ordering of nodes. However, most of the existing generative models for graphs are not invariant to the chosen ordering, which might lead to an undesira…
Graph neural networks leverage graph filters to learn from network data.
problem Learning from network data with graph structure.
method Characterize graph neural networks using graph signal processing and graph convolutional filters.
result Graph neural networks have permutation equivariance and stability to topology changes.
Theoretical guarantees for permutation-equivariant QNNs avoid barren plateaus.
problem Excessive local minima and barren plateaus in QNNs training landscapes.
method Designing Sn-equivariant QNNs to encode permutation symmetry. result Equivariant QNNs do not suffer from barren plateaus, quickly reach overparametrization, and generalize well.
A2I Transformer predicts atom energies from coordinates, avoiding heavy featurization.
problem Efficiently predicting atom energies from molecular coordinates with minimal featurization.
method End-to-end model using self-attention, permutation-equivariant.
result Stable predictions with significantly smaller errors than molecular dynamics simulations.
NERS improves RL by sampling diverse transitions considering local and global contexts.
problem Sampling biases in experience replay lead to redundant transitions.
method Neural Experience Replay Sampler (NERS) that considers both local and global contexts.
result NERS significantly improves RL performance by sampling diverse and meaningful transitions.
New graph foundation models respect symmetries for broader applicability.
problem Tailored graph machine learning architectures limit broader applicability.
method Investigates symmetries for label and feature permutations, proving network universal approximator.
result Universal approximator on multisets respecting node and feature permutations.
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder that avoids this re…
We introduce a simple permutation equivariant layer for deep learning with set structure.This type of layer, obtained by parameter-sharing, has a simple implementation and linear-time complexity in the size of each set. We use deep permutation-invariant networks to perform point-could classification and MNIST-digit sum…
In this paper we introduce a new neural architecture for sorting unordered sequences where the correct sequence order is not easily defined but must rather be inferred from training data. We refer to this architecture as OrderNet and describe how it was constructed to be naturally permutation equivariant while still al…
This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.
problem Measuring and ranking uncertainty in multi-agent multi-modal trajectory forecasting.
method Proposes collaborative uncertainty (CU) and a CU-aware regression framework.
result The CU-aware regression framework improves SOTA systems' performances.
Weisfeiler and Leman enhance graph learning for machine learning tasks.
problem Learning from graph data in machine learning.
method Weisfeiler and Leman algorithm applied to graph and node representation learning.
result The algorithm improves graph and node representation learning in machine learning.
Improves modeling of sets with permutation invariant densities.
problem Challenges in calculating trace limit practicality of current methods.
method Proposes an alternative approach to define permutation equivariant transformations with closed form trace.
result Improves both training and final performance.
The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain. In comparison, there are a number of problems in which the…
We study the problem of designing models for machine learning tasks defined on \emph{sets}. In contrast to traditional approach of operating on fixed dimensional vectors, we consider objective functions defined on sets that are invariant to permutations. Such problems are widespread, ranging from estimation of populati…
Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others. GNNs consists of a cascade of layers, each of which applies a graph convolution, followed by a pointwise nonlinea…
HaKAN uses Hahn-KAN blocks to forecast multivariate time series.
problem Long-term time series forecasting challenges with high complexity and spectral bias.
method HaKAN integrates channel independence, patching, and a stack of Hahn-KAN blocks with residual connections. It uses Hahn polynomial-based learnable activation functions.
result HaKAN consistently outperforms state-of-the-art methods on various forecasting benchmarks.
Study shows gMPNNs struggle with OOD link prediction in larger test graphs.
problem Inductive out-of-distribution link prediction in larger test graphs.
method Theoretical analysis and development of a gMPNN with structural pairwise embeddings.
result Structural node embeddings from gMPNNs converge to random guessing as test graphs grow.
Generative model for set-valued data using permutation invariant flows.
problem Modeling set-valued data with conditional generative models.
method Conditional generative probabilistic model using continuous normalizing flows with permutation equivariant dynamics.
result Significantly outperforms non-permutation invariant baselines in log likelihood and domain-specific metrics.
Generative models improved with smoothed score functions for better sample quality.
problem Improving generative models for better sample quality.
method Smoothed score functions based on factorial Gaussian kernels.
result Single noise level achieved 14.15 Fréchet inception distance on CIFAR-10.
Generative model for hypergraphs captures complex interactions without pairwise reductions.
problem Challenges in generating realistic hypergraphs with pairwise reductions.
method Structured stochastic diffusion on relaxed incidence matrices.
result Generative model preserves structure-aware noising and yields explicit Gaussian law.
SE-RRMs solve structured problems like Sudoku and ARC-AGI by enforcing symbol equivariance.
problem Structured reasoning problems like Sudoku and ARC-AGI.
method Symbol-equivariant recurrent reasoning models enforcing permutation equivariance.
result SE-RRMs outperform prior RRMs on 9x9 Sudoku and generalize to larger and smaller instances.
Theoretical analysis explains why models generalize after overfitting in modular addition.
problem Understanding why models generalize after overfitting in modular addition.
method Theoretical analysis and gradient descent behavior of two-layer quadratic networks and Transformers.
result Two-layer quadratic networks and simple Transformers generalize well after initially overfitting, indicating grokking.
This work extends implicit bias analysis to multiclass classification using a new loss framework.
problem The implicit bias of gradient descent on multiclass data without explicit regularization.
method Employing the PERM framework to introduce a multiclass extension of the exponential tail property.
result Extended implicit bias result to multiclass classification using a new loss framework.
Transformers approximate mean-field dynamics of indistinguishable particles.
problem Approximating the dynamics of indistinguishable particles in complex systems.
method Using transformers to model the mean-field dynamics of interacting particle systems.
result Theoretical bounds on the distance between true and transformer-obtained mean-field dynamics.