Research reveals how diversity impacts ensemble generalization in classification tasks.
problem Understanding the relationship between diversity and generalization in classification ensembles.
method Investigated diversity measurement, its relationship with generalization error, and pruning methods.
result Generalization error is reduced effectively only when diversity is increased in specific ranges, not in others.
New model improves diversity in question generation over text.
problem Inadequate evaluation metrics for diverse questions.
method Proposed a variational encoder-decoder model and evaluation scheme.
result Improved diversity in generated questions without loss of quality.
New method improves ensemble diversity and generalization.
problem Ensemble diversity does not guarantee practical generalization.
method Introduced a new diversity metric and training method for extrapolating differently on local data patches.
result Improves generalization and diversity in practical settings, especially under data limits and covariate shift.
Paper explores how text generation quality and diversity metrics relate to distribution fitting.
problem Unclear relation between text generation quality and diversity metrics and distribution fitting.
method Theoretical approach to prove a linear combination of quality and diversity metrics can be a divergence metric.
result CR/NRR proposed as a better substitute for BLEU/Self-BLEU metrics.
MO-PaDGAN generates diverse, high-performance designs with multiple metrics.
problem Challenges in generating diverse, high-performance designs with multiple metrics.
method MO-PaDGAN uses a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and performances.
result MO-PaDGAN expands the design space towards high-performance regions and generates new designs with high diversity and performances.
Proposes Vendi Score for evaluating diversity in ML models.
problem Lack of flexible diversity evaluation metrics in ML.
method Integrates ecological and quantum statistical mechanics concepts to define Vendi Score.
result Vendi Score enables flexible diversity evaluation without requiring a reference dataset.
Unified evaluation for both quality and diversity in NLP.
problem Measuring both quality and diversity in NLP models.
method Proposes HUSE, a metric combining human and statistical evaluation.
result HUSE detects both quality and diversity defects in NLP models.
PaDGAN generates diverse, high-quality designs with improved performance.
problem Lack of diversity and performance improvement in generated designs.
method Integrates Determinantal Point Processes for diversity and quality, using GAN framework.
result PaDGAN generates higher quality designs with better diversity and without mode collapse.
This paper improves model generalization by integrating diverse pretrained models.
problem Leveraging diverse pretrained models for robust out-of-distribution generalization.
method Characterize and integrate diverse pretrained models based on diversity and correlation shifts.
result Demonstrates state-of-the-art out-of-distribution generalization performance.
SharpBalance improves deep ensemble performance by balancing sharpness and diversity.
problem Improving deep ensemble performance in both in-distribution and out-of-distribution scenarios.
method Introducing SharpBalance, a novel training approach that balances sharpness and diversity within ensembles.
result SharpBalance effectively improves the sharpness-diversity trade-off and ensemble performance in ID and OOD scenarios.
New method reduces overfitting in deep neural networks by measuring and regulating hidden unit diversity.
problem Overfitting in deep neural networks.
method Introduces a new redundancy measure based on mutual information to improve generalization.
result Reduction of redundancy improves generalization capacity, reducing overfitting.
New framework predicts diverse, contextually plausible 3D human motions.
problem Predicting multiple plausible future 3D poses given observed poses.
method Developed a new variational framework that conditions latent variable on past observation to encourage relevant information.
result Our approach generates motions of higher quality and preserves contextual information.
Generative model learns diverse fixes for program errors.
problem Uncertainty in predicting a single fix for program errors.
method Deep conditional variational autoencoder with diversity regularizer.
result Strong improvements over state-of-the-art approaches, generating up to 45% diverse fixes.
Proposes a method to generate diverse outputs in conditional GANs.
problem Mode-collapse in conditional GANs, where outputs are overly simplified.
method Explicit regularization to produce diverse outputs based on latent codes.
result Demonstrates improved diversity in image-to-image translation, inpainting, and future video prediction tasks.
A framework generates diverse counterfactual explanations for machine learning models.
problem Creating understandable explanations for machine learning predictions.
method Framework based on determinantal point processes for generating and evaluating diverse counterfactuals.
result Framework generates diverse counterfactuals that approximate local decision boundaries better than prior approaches.
GRATIS generates diverse time series for benchmarking.
problem Lack of diverse time series data for evaluation.
method Uses mixture autoregressive (MAR) models to generate time series.
result Generates diverse and controllable time series efficiently.
Generating molecules with desired chemical properties is important for drug discovery. The use of generative neural networks is promising for this task. However, from visual inspection, it often appears that generated samples lack diversity. In this paper, we quantify this internal chemical diversity, and we raise the …
Diversity or complementarity of experts in ensemble pattern recognition and information processing systems is widely-observed by researchers to be crucial for achieving performance improvement upon fusion. Understanding this link between ensemble diversity and fusion performance is thus an important research question. …
Heterogeneous SVO leads to diverse policies in sequential social dilemmas.
problem Understanding how diverse social value orientations affect behavior in sequential social dilemmas.
method Extending prior reinforcement learning studies, we instantiated heterogeneous SVO in a sequential social dilemma setting and measured task-specific diversity metrics.
result Heterogeneous SVO leads to meaningfully diverse policies across various incentive structures.
This paper explores how diverse neural network ensembles improve prediction accuracy and robustness against deception.
problem Improving prediction accuracy and robustness of neural networks against adversarial attacks.
method Examines and measures ensemble diversity, develops algorithms for creating and combining diverse ensembles.
result Greater diversity in neural network ensembles leads to higher accuracy and robustness against deception.
This paper presents a general framework for studying diverse beliefs in dynamic economies. Within this general framework, the characterization of a central-planner general equilbrium turns out to be very easy to derive, and leads to a range of interesting applications. We show how for an economy with log investors hold…
A new LLM-based method enhances diversity in oversampling for imbalanced classification.
problem Limited diversity in synthetic minority samples generated by current LLM-based approaches reduces robustness and generalizability.
method Condition synthetic sample generation on minority labels and features, use permutation strategy for fine-tuning, fine-tune on minority and interpolated samples.
result Significantly outperforms eight SOTA baselines in diverse synthetic sample generation and downstream classification tasks.
The paper teaches a reinforcement learning agent to generate diverse programs based on symbolic instructions.
problem Learning to generate diverse programs for diverse scenes given a symbolic instruction.
method Instruction-conditioned reinforced adversarial learning.
result The agent's stochastic policy more accurately captures the diversity in the goal distribution.
Proposes a method to generate diverse translations by conditioning on target domain.
problem NMT models lack diversity in translations, even with search algorithms.
method Condition the decoder on a latent variable representing target domain, generated by a target encoder.
result Generated diverse translations without affecting performance or training time.
Proposes MOGFNs for generating diverse Pareto optimal solutions in multi-objective optimization.
problem Generating diverse candidates in multi-objective optimization with conflicting objectives.
method Introduces MOGFNs based on GFlowNets, with two variants: MOGFN-PC and MOGFN-AL.
result Improved candidate diversity compared to existing methods.
New method improves text classification without labeled target data.
problem Improving text classification under domain shift without labeled target data.
method Diversity-based generalization using multi-head attention with diversity constraints.
result Method matches state-of-the-art performance without labeled target data.
Model predicts diverse chemical reactions for target compounds.
problem Making generalizable and diverse retrosynthetic reaction predictions.
method Transformer architecture with novel pre-training methods and a latent variable model.
result Improves performance on USPTO-50k dataset, generating more diverse predictions.
Improves GANs by enforcing diverse feature learning.
problem GANs can collapse to a single configuration and be unstable.
method Enforces diverse feature learning by penalizing correlated features.
result Enforces diverse features, stabilizes training, and improves image synthesis.
Ensemble of diverse CNNs detects and mitigates adversarial attacks.
problem Detecting and defending against adversarial attacks.
method An ensemble of specialized CNNs with a voting mechanism.
result Significant reduction in adversarial attack risk rate.
Proposes models to generate more interesting story endings.
problem Generating diverse and interesting story endings for a given context.
method Trains models to focus on keyphrases and promotes non-generic words.
result Models generate more diverse and interesting story endings.
Paper proposes metrics to evaluate both quality and diversity in text generation models.
problem Existing metrics only evaluate quality or diversity, not both.
method Approximate the distance between generative model and real data distribution using n-gram and BERT features.
result Proposed metrics better evaluate both quality and diversity of text generation models.
The paper extends deep multi-task learning to diverse domains, finding shared functionality.
problem General problem solving from diverse deep learning tasks.
method Decomposes tasks into subproblems, optimizing sharing through stochastic algorithm.
result Joint learning across diverse domains and architectures improves performance.
Proposes DC3-GAN for diverse unsupervised conditional generation.
problem Low diversity in unsupervised conditional generation.
method Integrates encoder-generator pair with generator-encoder pair to enhance diversity.
result Improves clustering performance and disentanglement of latent variables.
New measures quantify how data augmentation improves model performance.
problem Understanding the effectiveness of data augmentation in deep learning.
method Introduced Affinity and Diversity measures to quantify augmentation performance.
result Augmentation performance is best achieved by optimizing both Affinity and Diversity.
CPRA efficiently finds diverse solutions in CO problems using UL and parallelization.
problem Finding optimal solutions often requires diverse outcomes in real-world applications.
method CPRA, an UL-based framework, discovers shared representations to generate diverse solutions.
result CPRA outperforms existing UL-based solvers in generating diverse solutions.
This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.
problem Generating effective ensembles of neural networks for multi-modal data.
method Explicitly optimize a diversity inducing adversarial loss for learning stochastic latent variables.
result Significant improvements in classification accuracy and out-of-distribution detection compared to baselines.
Self-distillation improves model performance by increasing teacher diversity and smoothing predictions.
problem Improving model generalization and performance through self-distillation.
method Interpreting self-distillation as MAP estimation and proposing instance-specific label smoothing.
result Self-distillation enhances model performance by increasing teacher diversity and smoothing predictions.
This work generates diverse adversarial attacks for different domains using latent variable perturbation.
problem Adversarial attacks on deep neural networks are limited to a single perturbation.
method Frame adversarial attacks as learning a distribution of perturbations, enabling generation of diverse attacks.
result Framework generates competitive or superior adversarial attacks across diverse domains (images, text, graphs).
DASH improves ensemble generalizability by encouraging diverse, flat loss landscapes.
problem Improving generalization and robustness of deep ensembles.
method DASH promotes diversity and flatness in deep ensembles by encouraging base learners to move towards low-loss regions of minimal sharpness.
result DASH improves ensemble generalizability, as demonstrated by extensive empirical evidence.
Generative model learns diverse generations using DPP to avoid mode collapse.
problem Mode collapse in generative models, limiting output to few modes.
method Inspired by DPP, proposes an unsupervised penalty loss to enhance diversity.
result Generative DPP approach consistently resists mode-collapse and outperforms state-of-the-art methods.
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.
MAP-Elites generates diverse trading strategies for improved execution performance.
problem Optimizing trading execution schedules in volatile market conditions.
method Quality-diversity algorithm (MAP-Elites) generating a portfolio of specialized strategies.
result Diverse strategies achieve 8-10% performance improvements, validating quality-diversity methods.
SteinGen generates diverse graph samples from a single example.
problem Generating graphs with characteristic structures and diversity from a single example.
method Combines Stein's method and MCMC with Glauber dynamics and re-estimation of the Stein operator.
result High distributional similarity to the original data, combined with high sample diversity.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
Mixreg improves RL generalization by mixing diverse training environments.
problem Overfitting in RL agents trained in limited environments.
method Trains on a mixture of diverse observations and imposes linearity constraints.
result Mixreg outperforms baselines on unseen testing environments.
Proposes SLCVAE to improve text diversity by self-labeling.
problem KL-Vanishing problem in CVAE for diverse text generation.
method Explicit optimizing objective to guide encoder towards best encoder, using a labeling network.
result Improves text diversity while maintaining comparable accuracy.
New measures quantify diversity of latent representations using metric space magnitude.
problem Evaluating the diversity of latent representations in machine learning models.
method Developed magnitude-based measures for latent representations, stable under data perturbations.
result Demonstrated superior performance across various domains and tasks.
New SLC distributions enable easier control over diversity.
problem Lack of easy control over diversity in existing models.
method Developed strongly log-concave distributions and two tools for sampling and mode finding.
result Established weak log-submodularity for SLC functions and optimization guarantees for mode finding.