New approach reduces GAN violence by fostering peaceful coexistence.
problem Quantifying and addressing the effects of GAN violence.
method Proposes Generative Unadversarial Networks (GUNs) to train two models in harmony.
result GUNs achieve both moral and log-likelihood high ground.
System classifies metaphorical violence on cable news.
problem Identifying and annotating metaphorical violence in cable news.
method Neural network trained on user annotations of metaphor.
result System can classify metaphors by context, subject, or verb.
New method detects psychosocial factors linked to gang violence on social media.
problem Detecting psychosocial factors in gang-related social media posts.
method Multimodal analysis of tweets with images and text, using various classification methods.
result Multimodal approach improves classification performance by 18%.
Machine learning improves risk assessment for gender-based violence victims.
problem Accurately predicting recidivism risk in gender-based crime victims.
method Applied machine learning techniques to create models predicting recidivism risk.
result Proposed ML method outperforms classical statistical methods.
We first pursue the study of how hierarchy provides a well-adapted tool for the analysis of change. Then, using a time sequence-constrained hierarchical clustering, we develop the practical aspects of a new approach to wavelet regression. This provides a new way to link hierarchical relationships in a multivariate time…
The July Revolution in Bangladesh was fueled by state violence, which paradoxically strengthened the movement.
problem Understanding how state repression can paradoxically lead to increased mobilization during civil resistance.
method Mixed-methods approach combining qualitative narrative and quantitative analysis using machine learning and statistical modeling.
result The July Revolution was driven by a contingent, non-linear backfire effect triggered by specific catalytic moral shocks and accelerated by the viral reaction to state brutality.
Decision tree predicts DV recidivism with interpretable models.
problem Predicting DV re-offending to aid risk assessment and victim protection.
method Employed decision tree induction to balance accuracy and interpretability, addressing class imbalance and feature selection.
result Achieved comparable accuracy with 3 features and understandable 4-node trees.
Paper proposes a framework to analyze DV on social media.
problem Lack of actionable knowledge from DV social media data.
method Develops a novel framework to model and discover themes related to DV.
result Provides actionable knowledge from DV social media content.
Neural networks improve scalability for agent-based modeling demonstrations.
problem Scalability issues in training models of dynamic systems from demonstrations.
method Use of neural networks to reduce the search space for agent-level parameters.
result More scalable architecture for reproducing emergent behavior from demonstrations.
We model anomaly and change in data by embedding the data in an ultrametric space. Taking our initial data as cross-tabulation counts (or other input data formats), Correspondence Analysis allows us to endow the information space with a Euclidean metric. We then model anomaly or change by an induced ultrametric. The in…
This study predicts crime trends in Denver using machine learning.
problem Predicting crime patterns to aid law enforcement and resource allocation.
method Statistical analysis, data visualization, and various classification algorithms.
result Ensemble Model 4 achieved the highest accuracy in predicting crime.
Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include ec…
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
problem Addressing mode collapse and likelihood issues in GANs and autoencoders.
method Explains various GAN and autoencoder variants, their applications, and methods to resolve issues.
result Various methods to resolve mode collapse and improve likelihood in GANs and autoencoders.
A new GAN model α-GAN with tunable loss function addresses gradient vanishing and mode collapse issues.
problem Addressing vanishing gradients and mode collapse in GANs.
method Introduced a tunable GAN α-GAN using a supervised α-loss function. result Holistic understanding of α-GAN related to Arimoto divergence and convergence properties. Unbalanced GANs stabilize GAN training by pre-training the generator with VAE.
problem Stable training of GANs to avoid mode collapses and improve image quality.
method Pre-train GAN generator with VAE, balance generator and discriminator training, prevent discriminator's early convergence.
result Unbalanced GANs reduce mode collapses and outperform ordinary GANs in stability, convergence, and image quality.
GANs can approximate SDEs for large time steps.
problem Approximating SDEs for large time steps using GANs.
method Proposed a conditional GAN architecture to enable strong approximation of SDEs.
result Supervised GAN outperformed standard GAN and other schemes in strong error.
Fisher GAN improves GAN training stability and efficiency.
problem Stable training of GANs with minimal data constraints.
method Integrates Fisher information into IPM framework for GAN training.
result Fisher GAN achieves stable and efficient training without compromising critic capacity.
Paper bridges f-GANs and WGANs for better image generation.
problem Learning high-dimensional distributions using GANs.
method List constraints, minimize Lagrangian relaxation, propose KL-Wasserstein GAN.
result Empirical success on synthetic and real-world image generation benchmarks.
MD-GAN distributes GAN training across multiple workers for efficiency.
problem Training GANs on large, distributed datasets.
method Proposes a novel learning procedure for GANs to work in a distributed setup.
result Reduces learning complexity by a factor of two on each worker node.
Clarifies bias in GAN loss functions and improves MMD GAN training.
problem Bias in GAN loss functions and training strategies.
method Analyzes MMD GANs, discusses kernel choice, proposes convergence measure.
result Gradient estimators are unbiased but learning a discriminator leads to biased gradients for the generator.
E-GAN improves GANs by evolving a population of generators.
problem Training instability and mode collapse in GANs.
method E-GAN uses mutation operations as different adversarial training objectives to evolve a population of generators.
result E-GAN achieves better generative performance and reduces training problems.
City-GAN learns city architecture styles using a custom GAN architecture.
problem Learning architectural styles of cities using standard GAN and CGAN architectures.
method Proposes a custom GAN architecture to improve learning of city architectural styles.
result Demonstrates superior performance of custom GAN architecture for city architectural style learning.
SR-GANs combat mode collapse in GANs by monitoring and compensating spectral distributions.
problem Mode collapse in GANs.
method Spectral regularization (SR-GANs) to combat spectral collapse.
result SR-GANs prevent mode collapse and outperform SN-GANs in experiments.
WGAN uses a smoother metric to train GANs better.
problem Difficulty in training GANs.
method Introducing Wasserstein GAN to improve GAN training.
result Wasserstein GAN improves training stability and effectiveness.
FCC-GAN combines fully connected and convolutional layers for improved GAN performance.
problem Lack of understanding in choosing GAN network architectures.
method Proposes FCC-GAN, a hybrid architecture combining fully connected and convolutional layers.
result FCC-GAN outperforms traditional GAN architectures in terms of learning speed and sample quality.
Gradient descent GAN optimization is locally stable under certain conditions.
problem Understanding and stabilizing GAN optimization.
method Analysis of gradient descent GAN optimization, showing local asymptotic stability.
result Gradient descent GAN optimization is locally stable under proper conditions.
GANs approximate manifold regularization for semi-supervised learning.
problem Semi-supervised learning with limited labeled data.
method Approximate Laplacian norm using GANs for manifold regularization.
result State-of-the-art results on CIFAR-10 dataset with easier implementation.
GANs with NCE improve dihedral angle prediction accuracy.
problem Inaccurate distribution of predicted dihedral angles.
method Introduced NCE-GAN to estimate density of GAN models and proposed residue-wise variants of AC-GAN and Semi-supervised GAN.
result Improved distribution of predicted angles, most similar to real angles with Semi-supervised GAN.
Prb-GAN uses dropout and variational inference to improve GAN performance.
problem GANs struggle with mode loss and training instability.
method Introduces Prb-GANs with dropout and variational inference for parameter distribution.
result Improves GAN performance through dropout and variational inference.
MH-GAN uses a discriminator to improve sampling from a GAN's distribution.
problem Improving sampling from a GAN's implicitly defined distribution.
method Combines Markov chain Monte Carlo and GANs, using a discriminator to wrap the generator.
result MH-GAN samples from the true distribution even when the generator is imperfect.
xAI-GAN improves GANs by providing richer feedback, enhancing image quality.
problem Challenges in GAN training, especially resource-intensive and data-intensive.
method Integrates xAI systems to provide richer corrective feedback from discriminators to generators.
result Improves image quality by up to 23.18% on MNIST and FMNIST datasets.
This paper reviews GANs algorithms, theory, and applications.
problem Lack of comprehensive study on GANs connections and evolution.
method Detailed introduction of GANs algorithms, theoretical investigation, and application illustrations.
result Comprehensive review of GANs from algorithms, theory, and applications perspectives.
New method compresses GANs by 1669:1 ratio on MNIST, 58:1 on CIFAR-10, 87:1 on Celeb-A.
problem Expensive GANs for low SWAP hardware and real-time applications.
method Knowledge distillation between a student and teacher GAN.
result Compressed GANs outperform standard training methods with a fixed parameter budget.
Generative models create paintings that match training data.
problem Creating realistic paintings using machine learning.
method Used Spectral Normalization GAN (SN-GAN) and SN-GAN with Gradient Penalty to generate paintings.
result SN-GAN produced paintings most comparable to the training dataset.
GANs may not have Nash equilibria, but proximal training can find solutions.
problem Existence of Nash equilibria in GANs optimization.
method Proximal training approach to find solutions.
result Proximal training finds solutions to GAN problems.
GANs generate images of emotions from datasets.
problem Creating realistic images of emotions from datasets.
method Used GANs and StarGAN to train on datasets of emotions.
result StarGAN successfully generated images of 7 basic emotions.
Empirical study shows GANs overfit and drop modes when training is deterministic.
problem Understanding overfitting and mode drop in GAN training.
method Empirical analysis of GAN training with and without stochasticity.
result GANs overfit and drop modes when training is deterministic.
TAC-GAN improves image diversity in AC-GAN by minimizing class distribution divergence.
problem Low diversity in AC-GAN's generated samples as class count increases.
method TAC-GAN introduces twin auxiliary classifiers to address class separability issues.
result TAC-GAN effectively minimizes divergence between generated and real data distributions.
GANs analyzed for performance and training issues.
problem Performance and training issues of GANs.
method SDE approximations for training GANs.
result Improved understanding of GANs through analytical perspectives.
BC-GANs use randomness in generator for better unsupervised learning.
problem Improving unsupervised learning performance.
method Bayesian framework with random generator for deterministic input.
result BC-GANs outperform state-of-the-arts in experiments.
Vanilla GANs are connected to Wasserstein distance for better understanding.
problem Understanding the statistical properties of Vanilla GANs.
method Connecting Vanilla GANs to Wasserstein distance and proving an oracle inequality.
result An oracle inequality for Vanilla GANs in Wasserstein distance is obtained.
Coulomb GANs optimize GANs to generate diverse samples without mode collapse.
problem GANs often generate only a subset of target distribution modes.
method Model GAN learning as a potential field of charged particles, where generated samples attract training set samples and repel each other.
result Coulomb GANs converge to a single Nash equilibrium that matches the target distribution.
GANs improve anomaly detection, faster and better.
problem Anomaly detection in high-dimensional data.
method Leveraging recent GAN models for anomaly detection.
result State-of-the-art performance on image and network intrusion datasets, 400x faster.
Unified framework compresses GANs up to 47x with minimal quality loss.
problem High parameter complexity of GANs for resource-constrained devices.
method Unified optimization framework combining model distillation, channel pruning, and quantization.
result 47x compression of CartoonGAN with minimal quality degradation.
NR-GANs learn clean images from noisy data.
problem Learning clean images from noisy training data.
method Introduced a noise generator and distribution/transformation constraints.
result NR-GANs can generate clean images from noisy data.
New method improves GANs by estimating density ratios in feature space with SP loss.
problem Filtering out unrealistic images from GANs trained with suboptimal discriminators.
method Develops DRE-F-SP method based on Softplus loss for density ratio estimation in feature space, and proposes three subsampling methods.
result Empirically shows substantial improvement over existing methods on synthetic and CIFAR-10 datasets.
Fence GAN improves anomaly detection by modifying GAN loss.
problem Anomaly detection on complex high-dimensional data.
method Modified GAN loss to encourage generated samples at the boundary of real data distribution.
result Fence GAN yields the best anomaly classification accuracy.
This work improves GAN stability with theoretical conditions.
problem GANs exhibit unstable behavior during training.
method Developed a theoretical framework and conditions for GAN stability.
result Constructs a GAN that fulfills stability conditions.