Graphical models and tensor networks are shown to be dual.
problem No specific problem stated; focuses on the duality between models.
method Study of tensor hypernetworks on hypergraphs and their correspondence to graphical models.
result Tensor hypernetworks on hypergraphs correspond to graphical models of the dual hypergraph.
A new hypernetwork architecture improves link prediction in knowledge graphs.
problem Link prediction in incomplete knowledge graphs.
method Hypernetwork architecture generating simplified relation-specific convolutional filters.
result Hypernetwork outperforms ConvE and previous approaches across standard datasets.
TensorHyper-VQC improves VQC scalability and robustness.
problem Scalability and noise sensitivity in VQC.
method Tensor-train-guided hypernetwork framework.
result TensorHyper-VQC achieves superior performance and robust noise tolerance.
Optimizes neural networks using hypernetworks for better likelihood.
problem Maximizing conditional likelihood of neural networks.
method Optimizes hypernetworks to directly maximize likelihood.
result Competitive results on regression and classification benchmarks.
Wide hypernetworks don't guarantee convergence under gradient descent.
problem Theoretical guarantees for wide hypernetworks in over-parameterized settings.
method Analyzing infinitely wide hypernetworks and their convergence properties.
result Infinitely wide hypernetworks do not guarantee convergence to a global minimum under gradient descent.
Task-conditioned hypernetworks help neural networks learn multiple tasks without forgetting.
problem Catastrophic forgetting in neural networks when sequentially trained on multiple tasks.
method Task-conditioned hypernetworks that generate target model weights based on task identity.
result Task-conditioned hypernetworks achieve state-of-the-art performance on CL benchmarks and retain long memories.
Hypernetworks are simplified simplicial complexes with curvature.
problem Representing hypernetworks geometrically for analysis.
method Hypernetworks are interpreted as posets, which are simplicial complexes with Forman Ricci curvature.
result Hypernetworks have intrinsic curvature that correlates with their Euler characteristic.
Graph hypernetworks improve molecule property prediction and classification.
problem Improving molecule property prediction and classification using graph neural networks.
method Replacing underlying networks with hypernetworks and addressing training instability.
result Demonstrated state-of-the-art performance in various benchmarks.
Neural networks generate their own weights using hypernetworks.
problem Generating diverse and non-trivial weights for neural networks.
method Formulate a compromise between accuracy and diversity, using multi-layered perceptrons for mapping.
result Generated weights are diverse and lie on a non-trivial manifold.
Two methods improve tensor recovery in Ising models, revealing gene interactions.
problem Improving tensor recovery in Ising models for complex data structures.
method Pseudolikelihood and interaction screening approaches for tensor learning.
result Both methods achieve tensor recovery with sample size logarithmic in nodes, exponential in strength and degree.
This paper compares hypernetworks and embedding methods for function approximation.
problem Learning to map inputs to functions efficiently for each instance.
method Compared embedding-based and hypernetwork methods using expressivity and complexity.
result Hypernetworks can be more efficient in terms of trainable parameters for certain functions.
Improved hypernetwork for efficient neural network hyperparameter tuning.
problem Efficiently optimizing hyperparameters in neural networks.
method Proposed Δ-STN architecture focusing on accurate best-response Jacobian approximation. result Significantly improved hyperparameter tuning accuracy and stability.
Graph HyperNetworks (GHN) speed up neural architecture search.
problem Expensive neural architecture search (NAS) requiring training thousands of networks.
method GHN models architecture topology and generates weights via graph neural network.
result GHNs can search nearly 10 times faster than other methods on CIFAR-10 and ImageNet.
A new image representation method using hypernetworks.
problem Representing images in a way that allows for continuous manipulation and analysis.
method Constructing a hypernetwork that maps pixel positions to colors, allowing for continuous image manipulation.
result Comparable image super-resolution results to existing methods using a single model.
This work introduces an integrative approach based on Q-analysis with machine learning. The new approach, called Neural Hypernetwork, has been applied to a case study of pulmonary embolism diagnosis. The objective of the application of neural hyper-network to pulmonary embolism (PE) is to improve diagnose for reducing …
Generative models can be unfair and unstable; new methods improve fairness and stability.
problem Generative models unfairly penalize minority data and suffer from MADness.
method Intentionally designed hypernetworks and regularization terms.
result Generative models are more fair, stable, and unbiased with new methods.
Bayesian hypernetworks learn to transform noise to parameter distributions for neural networks.
problem Approximate Bayesian inference in neural networks with complex parameter correlations.
method Train a Bayesian hypernetwork to transform a simple noise distribution to a complex posterior distribution over neural network parameters using variational inference.
result Bayesian hypernetworks can represent multimodal approximate posteriors with correlations between parameters and enable efficient sampling.
Unified framework for learning function representations using INRs and Transformers.
problem Scalability and efficiency limitations in existing generative models.
method Integrates INRs and Transformer-based hypernetworks into latent variable models.
result Improved scalability, expressiveness, and generalization over existing models.
Generative model creates diverse neural network weights efficiently.
problem Creating high-performance and diverse weights for neural networks.
method Trains a hypernetwork mapping latent vectors to high-performance weights, balancing accuracy and diversity.
result Generated weights form a diverse manifold, improving classification accuracy.
HyperST-Net uses hypernetworks to improve spatio-temporal forecasting.
problem Forecasting spatio-temporal data is challenging due to complex spatial and temporal factors.
method Proposes a framework based on hypernetworks with three modules: spatial, temporal, and deduction.
result Models achieve significant improvements over state-of-the-art baselines.
End-to-end framework classifies cognitive workload in real-time driving scenarios.
problem Challenging task of classifying human cognitive states from behavioral and physiological signals.
method End-to-end framework using mixture Hyper Long Short Term Memory Networks (HyperNetworks).
result Framework outperforms previous methods with 83.9% precision and 87.8% recall.
Single training run learns optimal VAE parameters for various β values.
problem Training VAEs with varying β values for optimal trade-off between distortion and rate.
method Introduced Multi-Rate VAE (MR-VAE) using hypernetworks to map β to optimal parameters.
result MR-VAEs can construct the full rate-distortion curve without additional training.
HKF uses neural networks to adapt Kalman filters for dynamic channel tracking.
problem Tracking channels with varying dynamics and Doppler values.
method Combines Kalman filters with hypernetworks for dynamic adaptation.
result HKF achieves up to 2dB gain over Kalman filters at high Doppler values.
Differentially private learning avoids iterative optimization in parameter space.
problem Differentially private training of neural networks
method Hypernetworks trained on public datasets
result Significantly reduces noise in parameter space
We compress large neural networks for quick adaptation to specific contexts.
problem How to quickly adapt a pretrained large neural network to specific contexts.
method Propose a Bayesian hypernetwork framework to compress the network and encourage sparsity.
result Generated compressed networks are significantly smaller than baseline methods.
Automatically designs analog circuits with deep learning.
problem Manual design of analog circuits is time-consuming and error-prone.
method Two-stage network with hypernetwork scheme and differential simulator.
result The method generates efficient and accurate circuit designs.
Proposes a framework for semi-supervised continual learning from sequentially arriving data.
problem Learning from data with changing task distribution over time, especially in domains with a mix of labeled and unlabeled data.
method Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL) framework with a hypernetwork and semi-supervised auxiliary classifier.
result Significant improvements in continual semi-supervised learning setting.
This paper introduces a new formulation of the Conic Gromov-Wasserstein distance for comparing complex network structures.
problem Comparing measures of unequal mass and complex network structures.
method Novel semi-coupling formulation and extension to hypernetworks.
result Establishes fundamental properties and robustness of CGW metric.
SVH-PSL uses Stein Variational Gradient Descent and Hypernetworks to improve Pareto set learning for expensive MOO.
problem Fragmented surrogate models and pseudo-local optima in expensive multi-objective optimization problems.
method SVH-PSL integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks to address fragmentation and pseudo-local optima.
result SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive MOO.
A new framework enables real-time task trade-off control.
problem Conflict between multiple related tasks in a fixed model capacity.
method Formulates MTL as a preference-conditioned multiobjective optimization problem; uses a hypernetwork-based neural network.
result A single model can handle different trade-off preferences among multiple tasks.
This paper won 1st place in forecasting and investment challenges, improving on meta-learning and parametric models.
problem Forecasting and investment challenges in time-series data.
method Hypernetworks and adversarial portfolios to design time-series models.
result Outperformed state-of-the-art meta-learning methods and conventional parametric models.
Bayes by Hypernet improves neural network uncertainty measures.
problem Overconfidence and lack of meaningful uncertainty measures in neural networks.
method Bayes by Hypernet (BbH) uses implicit distributions and neural networks to model complex distributions.
result Bayes by Hypernet achieves competitive accuracies and predictive uncertainties on MNIST and CIFAR5 tasks.
Neural decoders improve performance on large algebraic block codes.
problem Improving decoding performance for large algebraic block codes.
method Graph neural networks for message passing with hypernetworks and arctanh activation.
result Neural decoding outperforms traditional methods for various code families.
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
A scalable framework uses Langevin sampling to approximate neural network models of evolving processes.
problem Uncertainty quantification in neural network models of dynamic systems.
method Flexible data model based on NODE, joint learning of data model and posterior parameters, Langevin sampling.
result Demonstrated performance on chemical reaction and material physics data, compared favorably to variational inference.
Hypermodels improve exploration efficiency and accuracy.
problem Efficiently approximating Thompson sampling with large ensembles.
method Introducing hypermodels as a generalization of ensembles, including linear and neural network hypermodels.
result Hypermodels enable more accurate exploration and performance gains over Thompson sampling.
Blow converts non-parallel raw audio voices efficiently.
problem Voice conversion with non-parallel data.
method Single-scale normalizing flow with hypernetwork conditioning.
result Blow outperforms existing flow-based architectures in voice conversion.
Quantum computing improves training of binary neural networks.
problem Training binary neural networks (BiNNs) is challenging.
method Employing a Variational Quantum Algorithm to generate binary weights using quantum circuit measurements.
result The proposed methods improve trainability and generalization of BiNNs.
Paper proposes a method to control robots of different shapes efficiently.
problem Learning optimal control policies for robots of various shapes is challenging.
method Hierarchical architecture with hypernetworks and fixed attention mechanism.
result Method improves learning performance and generalizes to unseen morphologies.
CoDA adapts dynamics models to new physical systems by conditioning on context.
problem Generalizing to new physical systems with shared dynamics but different contexts.
method Context-informed dynamics adaptation (CoDA) using multiple environments and a hypernetwork.
result State-of-the-art generalization results on nonlinear dynamics.
DISCO predicts system states from short trajectories using an evolved operator.
problem Predicting next states of dynamical systems governed by unknown PDEs.
method DISCO uses a hypernetwork to generate parameters of a smaller operator network for state prediction.
result DISCO achieves state-of-the-art performance with fewer training epochs and generalizes well.
DRNets dynamically route instances to efficient transformations.
problem High inference costs due to static model capacity.
method Dynamic Routing Networks (DRNets) with RouterNets for branch selection.
result DRNets reduce inference costs with comparable performance.
A new algorithm optimizes multiple molecular properties efficiently.
problem Designing molecules with conflicting objectives and costly evaluations.
method Multi-objective Bayesian optimization with GFlowNets.
result HN-GFN samples diverse molecules from an approximate Pareto front.
New MTPP model offers interpretable predictions with state-of-the-art performance.
problem Inexpressive models lack interpretability, while neural models sacrifice interpretability for performance.
method Extends Hawkes process to a hypernetwork with a latent space, making it flexible and interpretable.
result Achieves state-of-the-art performance across various tasks and metrics.
We simplify Volterra process predictions by reducing dimensionality and using a tailored deep learning model.
problem Predicting the conditional law of Volterra processes with stochastic volatility is challenging due to high dimensionality and non-smoothness.
method We developed a stable dimension reduction technique onto a low-dimensional statistical manifold of non-positive curvature and introduced a sequentially deep learning model tailored to this geometry.
result Our model can approximate the conditional law of Volterra processes with approximation rates achievable only with very large networks.
TerraNova models Earth and societies as a unified system.
problem Modeling the physical Earth and human societies as a coupled system.
method TerraNova integrates physical Earth fields and societal indicators in their native geometries using encoders, cross-modal transformers, and a hypernetwork.
result TerraNova represents the physical Earth and societies without lossy averaging over borders, achieving competitive performance and spanning axes not represented by purpose-built encoders.
Novel NAS method balances performance and hardware metrics efficiently.
problem Challenging multi-objective optimization in neural architecture search.
method Parameterizes joint architectural distribution via hypernetwork conditioned on hardware features and preferences.
result Zero-shot transferability to new devices with representative and diverse architectures.
Study evaluates CL methods in RNNs, highlighting differences from feedforward networks.
problem Preventing catastrophic forgetting in RNNs processing sequential data.
method Comprehensive evaluation of CL methods, including elastic weight consolidation and hypernetworks.
result Weight-importance methods perform similarly regardless of sequence length but require more stability for high working memory demands.