SyNGLER generates synthetic networks efficiently while preserving key structural properties.
problem Efficiently generating realistic synthetic networks with preserved structural properties.
method SyNGLER uses latent space network models to learn and reconstruct node embeddings, then generates synthetic networks.
result SyNGLER produces synthetic networks that better preserve key network characteristics than existing approaches.
DeepWeightFlow generates diverse neural network weights efficiently.
problem Generating complete neural network weights efficiently and accurately.
method Flow Matching in weight space with Git Re-Basin and TransFusion.
result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.
Generative Adversarial Networks generate realistic network traffic data.
problem Generating realistic flow-based network traffic for evaluation of NIDS.
method Generative Adversarial Networks (GANs) with preprocessing for categorical attributes.
result Two of three preprocessing methods generate high quality flow-based network traffic.
Model-based neural networks generalize better than ReLU networks for sparse recovery.
problem Understanding and quantifying the superior generalization of model-based neural networks.
method Using complexity measures like global and local Rademacher complexities, the paper provides theoretical bounds on generalization and estimation errors.
result Model-based neural networks exhibit higher generalization capabilities for sparse recovery problems compared to ReLU networks.
MMGAN creates graphs with higher-order motifs for better network simulation.
problem Generative models fail to capture higher-order connectivity patterns in real-world networks.
method Combines multiple biased random walks to capture different motif structures.
result Outperforms NetGAN at creating graphs with accurate network motif statistics.
ALI model learns generation and inference networks adversarially.
problem Jointly learn generation and inference networks.
method Adversarial process between generation and inference networks.
result Competitive performance on semi-supervised tasks.
Paper compares GAN techniques for image generation and modification.
problem Improving image generation and modification techniques using GANs.
method Comparison of supervised and unsupervised GANs, addition of an encoder, use of Capsule Network as discriminator.
result Reconstruction and modification of images possible with GANs.
New tighter generalization bounds for deep networks like CNNs and ResNets.
problem Establishing tighter bounds for deep neural networks' generalization error.
method Introducing a new characterization of Lipschitz properties and margin-based data-dependent error bounds.
result Significantly tighter generalization bounds for deep neural networks, including CNNs and ResNets.
DCGANs generate drainage networks quickly from samples.
problem High computational costs in generating large numbers of drainage networks.
method DCGANs trained with connectivity-informed directional information.
result Connectivity-informed DCGANs outperform other methods in reproducing accurate drainage networks.
Machine learning improves network classification and model selection.
problem Quantifying suitability of generative models for network structures.
method Interpretable machine learning to classify simulated networks based on features and interactions.
result Specific network features and their interactions are crucial for distinguishing generative models.
New complexity measure explains better generalization with over-parametrization in neural networks.
problem Why neural networks generalize better with over-parametrization.
method Developed a novel complexity measure based on unit-wise capacities.
result Established a tighter generalization bound for two layer ReLU networks.
The paper analyzes how low-rank layers in neural networks improve generalization.
problem Understanding how low-rank layers affect generalization in neural networks.
method Applying Maurer's chain rule for Gaussian complexity to analyze rank and spectral norm constraints.
result Deep networks with low-rank layers achieve better generalization than those with full-rank layers.
Paper tackles optimal network compression for financial systems.
problem Optimal network compression for financial systems under shocks.
method Formulated as an NP-hard problem, studied systemic risk measures, and analyzed specific networks.
result Systemic fragility results no longer hold generally under shocks and heterogeneous networks.
Proves generic existence of spectral networks for many cases.
problem Existence of spectral networks for a broad range of spectral data.
method Generic existence proof for spectral networks.
result Proves existence for a large class of spectral data.
We develop a convex relaxation method for analyzing neural network generalization.
problem Analyzing the generalization of parallel positively homogeneous networks.
method Linking non-convex ERM to a convex optimization problem over prediction functions.
result Achieved generalization bounds with almost linear sample complexity in network width.
Generative Adversarial Trainer improves neural network robustness to adversarial perturbations.
problem Improving neural network robustness to adversarial perturbations.
method Alternately trains a classifier and generator network to generate and classify adversarial images.
result Significantly lowers the generalization error of the network.
Improves deep neural network generalization with Jacobian matrix bounds.
problem Deep neural networks' generalization error with arbitrary depth and width.
method Analysis of Jacobian matrix spectral norm for arbitrary non-linearities and pooling layers.
result Bounded spectral norm of Jacobian matrix ensures good generalization.
Generative adversarial networks model and generate physical therapy exercises.
problem Mathematical modeling of human movements in physical therapy.
method Generative adversarial network structure with discriminative and generative models trained concurrently.
result Ability to classify and generate motion examples that resemble recorded sequences.
Self-teaching networks improve deep neural networks' generalization.
problem Improving deep neural networks' generalization capacity.
method Generates soft supervision labels to train lower layers, using an auxiliary loss to mimic the output layer.
result Self-teaching network achieves consistent improvements and outperforms existing methods in speech recognition tasks.
Gradient descent methods for deep ReLU networks achieve optimal generalization rates.
problem Generalization of gradient descent methods for deep neural networks
method Establishing minimax-optimal rates for GD and SGD with deep ReLU networks
result Gradient descent methods for deep ReLU networks achieve optimal generalization rates
Improved deep neural network generalization through noise resilience.
problem Understanding and predicting generalization error of deep neural networks.
method Noise resilience measures to predict generalization error.
result Secured 5th position in the PGDL competition at NeurIPS 2020.
CapsuleGAN uses capsule networks in GANs for better image data modeling.
problem Improving image data modeling in GANs.
method CapsuleGAN uses capsule networks as discriminators in GANs, with a new objective function incorporating margin loss.
result CapsuleGAN outperforms standard GANs on image data modeling and semi-supervised classification.
Real networks exhibit nontrivial topological features such as heavy-tailed degree distribution, high clustering, and small-worldness. Researchers have developed several generative models for synthesizing artificial networks that are structurally similar to real networks. An important research problem is to identify the…
New method transplants specific neural networks to generic ones without training samples.
problem Learning massive tasks and categories requires collecting samples for all at once.
method Designs a functionally interpretable generic network and uses back-distillation for transplanting.
result Method without training samples outperforms with 100 samples.
PBN combines generative and discriminative capabilities in a neural network.
problem Combining generative and discriminative capabilities in neural networks.
method Convolutional PBN, sharing FF-NN embodiment, combining generative and discriminative qualities.
result PBN shows excellent qualities from either generative or discriminative viewpoint.
New method transplants specific neural networks into generic ones.
problem Learning massive tasks and categories requires collecting samples for all at once.
method Designing a functionally interpretable generic network and transplanting specific modules.
result Generic network can learn new categories without sample annotations.
Modular neural networks generalize better with less data.
problem Theoretical and practical understanding of how modularity improves neural network generalization.
method Theoretical analysis of sample complexity, development of a novel learning rule.
result Modular networks require fewer samples to generalize compared to nonmodular networks, especially in high-dimensional tasks.
Generator network replicates AAM's face recognition neuron responses.
problem Replicating AAM's face recognition neuron responses using a deep generative model.
method Using a variational auto-encoder, learned generator network from face images generated by AAM, capturing shape variations without explicit shape model.
result Inferred latent variables of the learned generator network have strong linear relationship with AAM's shape and appearance variables.
Generative neural networks generate complex geological patterns with conditioning.
problem Generating complex geological patterns with spatial observations.
method Extending a generator network with a second inference network to learn conditioning.
result Parametrization for direct generation of conditional realizations.
Improves stability in hyperbolic neural networks for complex data generation.
problem Numerical instability in hyperbolic neural networks hinders complex architecture development.
method Proposes a novel hyperbolic AE-GAN architecture with stable layers.
result Demonstrates state-of-the-art performance in generating complex data.
DFM model detects communities in weighted networks without distributional assumptions.
problem Challenges in community detection for weighted networks.
method Distribution-Free Model (DFM) for weighted networks, using spectral clustering.
result Spectral clustering yields consistent community detection under DFM.
Deep residual networks trained with gradient descent have small generalization gap.
problem Limited theoretical understanding of why residual networks generalize well.
method Analyzing overparameterized deep residual networks trained by gradient descent.
result Demonstrates that residual networks have a small generalization gap between training and test error.
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.
CnGAN generates synthetic user preferences for non-overlapped users in cross-network recommender systems.
problem Cross-network recommender solutions ignore non-overlapped users, limiting their applicability.
method Multi-task learning, encoder-GAN architecture, user-based pairwise loss function.
result Generated user preferences improve recommendations for non-overlapped users, achieving superior performance.
Affine spiking neural networks learn efficiently and generalize well.
problem Learning with spiking neural networks, especially with positive weights.
method Affine encoders and decoders, continuous parameter dependence, gradient-based training.
result Affine spiking neural networks can approximate shallow ReLU networks and generalize well.
The study quantifies deep learning generalization error using data distribution and network smoothness.
problem Understanding the generalization error in deep learning models.
method Introducing cover complexity (CC) to measure data difficulty and using the inverse of the modulus of continuity to quantify neural network smoothness. A bound for expected accuracy/error is derived considering both CC and neural network smoothness.
result The expected error of trained neural networks scales with the square root of the number of classes and has a linear relationship with respect to the cover complexity.
Graphical-GAN combines Bayesian networks and GANs for structured data modeling.
problem Modeling structured data with complex dependencies.
method Integrates Bayesian networks and GANs, introduces structured recognition model, and generalizes EP algorithm.
result Successfully learns discrete and temporal structures on visual datasets.
Study reveals similarity between GAN generator and discriminator networks.
problem Understanding the structure and similarity of GAN networks.
method Examined the weights and structure of GAN networks, focusing on generator and discriminator similarities.
result Both GAN generator and discriminator networks have a similar structure, as evidenced by experimental results.
A new method learns text network embeddings by combining generative autoencoder and homophilic priors.
problem Improving performance of network learning applications, especially for textual networks.
method Variational Homophilic Embedding (VHE) - a fully generative model that optimizes a variational autoencoder for semantic information and a homophilic prior for structural information.
result VHE outperforms existing methods in various tasks on real-world textual networks.
BON improves deep neural network generalization by creating synthetic data support.
problem Overfitting in deep neural networks for supervised learning.
method BON uses a generative network to create synthetic data points around original data points, preventing decision boundaries from overfitting.
result BON++ improves convergence on CIFAR-10 compared to BON, and visualizes better boundaries on Iris dataset.
The study characterizes conditions for trainability and generalization in deep neural networks.
problem Understanding the conditions for deep neural networks to be trainable and generalize well.
method Analysis of Neural Tangent Kernel (NTK) for wide and deep networks.
result Large regions of hyperparameter space exist where networks can memorize training data but fail to generalize.
Synthetic social networks closely match real-world interactions.
problem Evaluating realism of synthetic social contact networks.
method Used multiple measures of graph complexity to compare synthetic networks with stylized models and empirical data.
result Synthetic networks are more realistic than stylized models.
DAMNETS generates complex network dynamics models.
problem Generating flexible and scalable models for network time series is challenging.
method Deep autoregressive model for Markovian network time series.
result DAMNETS outperforms other methods in sample quality.
Improves deep network generalization for image sequence reconstruction.
problem Improving generalization of deep networks for inverse image reconstruction.
method Proposes a network optimized by a variational approximation of the information bottleneck principle with stochastic latent space.
result Demonstrates improved generalization ability of inverse reconstruction networks through stochasticity and information bottleneck.
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
Theoretical work shows overparameterized networks generalize better due to weight clustering and feature exploration.
problem Understanding why larger models generalize better in machine learning.
method Theoretical analysis of a 3-layer convolutional neural network extended from the XOR problem, demonstrating interplay between weight clustering and feature exploration.
result Gradient descent converges to global minima with better generalization performance in overparameterized networks compared to smaller networks.
SGD on wide neural networks generalizes well, with bounds independent of width.
problem Generalizing from training data to unseen data in wide neural networks.
method Stochastic Gradient Descent (SGD) on over-parameterized ReLU networks.
result Generalization error bound of ildeO(n−1/2) independent of network width. Study bounds graph neural networks' over-parameterized error.
problem Understanding graph neural networks' performance in over-parameterized regimes.
method Developed mean-field regime bounds for graph convolutional and message passing neural networks.
result Established upper bounds with a convergence rate of O(1/n) for generalization error.