CutMix enhances feature learning in neural networks, improving test accuracy.
problem Understanding and improving feature learning in neural networks using patch-level augmentation.
method Three distinct methods: vanilla training, Cutout training, and CutMix training were studied.
result CutMix training yields the highest test accuracy and learns all features and noise vectors evenly.
Study how models represent features in naturalistic learning problems.
problem Understanding which features models use and ignore in naturalistic tasks.
method Synthetic datasets with controlled task-relevance of features, training models to recognize both easy and hard features.
result Models preferentially represent task-relevant features and suppress task-irrelevant ones over training.
BN helps learn fragile features, which can improve adversarial robustness.
problem The role of batch normalization in adversarial training and its impact on robustness.
method Investigated the expressiveness of BN in learning robust features compared to random features.
result Adversarially fine-tuning BN layers can result in non-trivial adversarial robustness.
Generative model uses random convolutional features to create financial time series.
problem Generating realistic financial time series with limited data and avoiding overfitting.
method Train generators by matching random convolutional features of real and generated time series, using SOCK (SOft Competing Kernels) feature map.
result Generators trained with random SOCK features outperform baselines across various financial datasets.
Proposes a method to update model weights by dynamically changing features during training.
problem Updating model weights efficiently during training.
method Dynamic feature replacement during training to update model weights.
result Increased model accuracy with same training time and complexity.
VPFD uses vocoder features for adversarial training in VC.
problem Adversarial training on waveform data is time-consuming and memory-intensive.
method VPFD employs vocoder features for adversarial training.
result VPFD achieves VC performance comparable to waveform discriminators with reduced training time and memory.
Reduces risk of model inversion by reducing sensitive feature influence.
problem Model inversion attacks reveal sensitive individual data from trained models.
method Privacy-guided training to reduce sensitive feature influence in tree-based models.
result Training models to reduce sensitive feature influence reduces the risk of inference attacks.
Training-free GNNs use labels as features to improve node classification.
problem Improving graph neural networks for transductive node classification.
method Advocates labels as features, designs training-free GNNs based on this.
result Training-free GNNs outperform traditional GNNs in node classification.
Large learning rates cause oscillations in NN weights that improve generalization.
problem Improving generalization of neural networks trained with large learning rates.
method Theoretical analysis and feature-noise data generation model.
result Oscillating SGD with large learning rates benefits NN generalization by effectively learning weak features.
Study models deep learning training dynamics using locally elastic SDEs to reveal feature separability.
problem Understanding how deep learning models separate features from different classes during training.
method Modeling deep learning training using locally elastic SDEs with a drift term reflecting backpropagation impact.
result Local elasticity in SDEs leads to linear separability of features, resulting in vanishing training loss.
Deep networks learn spurious features instead of actual object features, leading to poor generalization.
problem Deep networks' poor generalization on out-of-distribution samples due to learning spurious features.
method Evaluation of existing robust feature learning methods and regularization methods, comparison against a baseline designed to capture high correlation features.
result A baseline method trained on high correlation features outperforms existing methods in generalization.
New findings show that minimal feature diversity at neural network initialization is harmful but can be mitigated with noise.
problem The importance of feature diversity at neural network initialization.
method A series of experiments comparing different initialization schemes, including adding noise.
result Minimal feature diversity is harmful but can be mitigated with noise, even standard GPU noise is sufficient.
Grokking occurs when neural networks transition from lazy to rich training dynamics, fitting initial features before generalizing.
problem Understanding why neural networks exhibit early train loss decrease without corresponding test loss improvement.
method Analyzing vanilla gradient descent on polynomial regression with a two-layer neural network, identifying sufficient statistics for test loss.
result Grokking arises when a network first attempts to fit a kernel regression solution with initial features, followed by late-time feature learning.
Securely trains fair models using homomorphic encryption.
problem Protecting sensitive features while testing model fairness.
method Fully homomorphic encryption for training and testing.
result Practical application to adult income data set.
Enhances ZSL models with biologically inspired feature enhancement.
problem Limited training data leads to poor feature extraction from pre-trained models.
method Dual-channel learning framework using auxiliary data sets.
result Improves ZSL model's generalization ability and achieves state-of-the-art results.
Supporting evidence for adaptive feature program across diverse models.
problem Analyzing feature learning in neural networks.
method Over-parameterized sequence models and feature error measure (FEM).
result FEM is decreasing during training of adaptive feature models.
Training shapes the geometry of neural network feature maps, revealing local area magnification.
problem Understanding how training affects the geometric structure of neural network feature maps.
method Analyzing the Riemannian geometry induced by neural network feature maps at infinite width and after training.
result Training breaks the symmetry of the geometry induced by random neural network feature maps, magnifying local areas along decision boundaries.
Develops method to train classifiers on incomplete feature datasets.
problem Training classifiers on datasets with missing feature subsets.
method Simultaneous training of neural networks and sparse coding.
result Classifier trained on incomplete features correctly separates original data.
This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.
problem Previous online knowledge distillation methods only utilized class probabilities, missing feature map information.
method Adversarial training framework to transfer feature map information; multiple networks trained simultaneously with discriminators.
result Our method performs better than direct alignment methods and is more suitable for online distillation.
Improves deep learning training by matching mini-batch distributions.
problem Overfitting and noise in mini-batch training.
method ITDM, which matches the moments of mini-batch distributions to reduce overfitting.
result ITDM reduces overfitting and improves DNN training.
Annotation guidelines used to guide the annotation of training and evaluation datasets can have a considerable impact on the quality of machine learning models. In this study, we explore the effects of annotation guidelines on the quality of app feature extraction models. As a main result, we propose several changes to…
Training only BatchNorm parameters achieves surprisingly high performance in deep networks.
problem Understanding the role and expressive power of affine parameters in BatchNorm.
method Investigating performance when training only BatchNorm parameters and freezing all other weights.
result BatchNorm achieves high performance by learning to disable around a third of random features.
New method controls sparse feature updates in deep networks.
problem Understanding sparse feature updates in deep networks during training.
method Iterative linearised training method to control sparse feature updates.
result Iterative linearised training surprisingly performs on par with standard training, requiring less frequent feature learning.
The paper addresses over-fitting in deep learning models trained on imbalanced data.
problem Over-fitting to minor classes in deep learning models trained on imbalanced data.
method Investigated feature deviation and proposed class-dependent temperatures (CDT) to compensate for it.
result CDT helps in overcoming feature deviation, improving model performance on test data of minor classes.
Gradient descent amplifies random features in neural networks to useful ones.
problem Generalization in neural networks trained on corrupted data.
method Characterization of feature-learning process in two-layer ReLU networks trained by gradient descent.
result Gradient descent amplifies random features to useful ones, achieving near optimal generalization error.
Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
Deep models learn spurious features correlated with target, but can still perform well.
problem Spurious correlations in feature learning.
method Empirical risk minimization and specialized group robustness training.
result Feature representations learned by ERM are competitive with specialized methods.
In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have …
AFR simplifies reducing reliance on spurious features, improving model performance.
problem Reducing reliance on spurious features for out-of-distribution generalization.
method Automatic Feature Reweighting (AFR) updates the model with a weighted loss.
result AFR improves model performance on benchmarks with minimal compute.
Mixup improves feature learning by mixing common and rare features.
problem Improving generalization in deep learning models.
method Mixup, a data augmentation technique, is applied to feature learning. Theoretical and experimental studies are conducted to understand its benefits.
result Mixup effectively learns rare features from common ones, leading to better generalization.
AFS-BM improves model accuracy by dynamically selecting features.
problem Feature selection challenges in ML, especially scalability and adaptability.
method Joint optimization for feature selection and model training with binary masking.
result AFS-BM achieves significant improvements in model accuracy and computational efficiency.
End-to-end model detects articulatory features from speech data.
problem Detecting articulatory features from speech data for various applications.
method Apply Listen, Attend and Spell (LAS) architecture and attention models.
result End-to-end training of manners and places of articulation detectors.
CLIP models robustness to spurious features is re-evaluated using a new dataset.
problem Existing robustness tests of CLIP models may not fully reflect their performance on spurious features.
method Crafted a new dataset (CounterAnimal) to reveal CLIP models' reliance on realistic spurious features.
result CLIP models are robust to spurious features learned from their training data, not ImageNet.
FeAT improves OOD generalization by learning richer features.
problem Improving feature learning for out-of-distribution (OOD) generalization.
method Feature Augmented Training (FeAT) iteratively augments and retains features from different subsets of training data.
result FeAT effectively learns richer features, boosting OOD performance.
Mixup helps learn both features in multi-view classification problems.
problem Learning both features in multi-view classification problems.
method Training with a specific instantiation of Mixup.
result Training with Mixup leads to learning both features for every class.
Deep neural networks have shown promising results for various clinical prediction tasks such as diagnosis, mortality prediction, predicting duration of stay in hospital, etc. However, training deep networks -- such as those based on Recurrent Neural Networks (RNNs) -- requires large labeled data, high computational res…
AutoFIS automatically selects important feature interactions for CTR prediction models.
problem Manual feature interaction design is inefficient and prone to noise.
method Two-stage algorithm: search stage relaxes feature interactions to continuous parameters, re-train stage refines model performance.
result AutoFIS significantly improves CTR and CVR of FM-based models.
Scalable feature selection improves GBDT model training speed.
problem Efficiently selecting features for GBDT models in high-dimensional settings.
method Developed a scalable forward feature selection method using group testing.
result Significant speedups in training time with competitive model performance.
Study predicts SGD test loss for structured features.
problem Understanding test loss dynamics in SGD for structured data.
method Solveable model of SGD on mean square loss for arbitrary covariance structure.
result Simpler Gaussian model accurately predicts test loss of nonlinear models.
Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been widely used in machine learning for security applications to improve generalization a…
Breaking symmetry in training data is key for generalization in feature learning kernels.
problem Grokking in algebraic tasks, where models perform well on training but fail on unseen data.
method Used Recursive Feature Machine (RFM) with AGOP to learn task-relevant features, breaking symmetry in training data.
result Generalization occurs only when symmetry in the training set is broken, and RFM generalizes by recovering underlying invariance group action.
Gradient descent learns useful features even in the NTK regime.
problem The ability of neural networks to learn useful features.
method Local convergence analysis of gradient descent with regularization.
result Gradient descent can capture ground-truth directions for feature learning even after the loss threshold is reached.
A new method selects the best feature selection technique for datasets.
problem Selecting the best feature selection method for unseen datasets.
method Data synthesis, meta features, fuzzy similarity, classification model training.
result Successfully recommended the best feature selection method for five out of eight datasets.
This work investigates how neural collapse improves transfer learning for large-scale models.
problem Improving transfer learning for large-scale models with limited labeled data.
method Investigates neural collapse and develops a fine-tuning method using skip-connections.
result Feature collapse on downstream data correlates with higher transfer accuracy.
Study shows how a strong model can learn a task's feature while retaining other capabilities.
problem How to align superhuman AI systems using weak-to-strong generalization.
method Two-layer neural networks, reward-model learning, multi-step SGD, feature learning.
result The strong model efficiently learns task features while retaining general capabilities.
A new feature selection method for semi-supervised learning with imperfect labels.
problem Feature selection for semi-supervised learning with imperfectly labeled data.
method Genetic algorithm for proposing feature subsets, probabilistic error model for mislabeling, multi-class C-bound selection criterion.
result Empirical results show the effectiveness of the proposed framework compared to state-of-the-art approaches.
A neural network approach for feature selection using mutual information.
problem Feature ranking and selection leading to sub-optimal solutions for class separability.
method Stochastic mutual information gradient estimation for dimensionality reduction.
result The network projects features onto an output space maximizing mutual information with class labels.
New algorithms identify invariant features for domain generalization.
problem Achieving robust models across unseen environments.
method Invariant-Feature Subspace Recovery (ISR) algorithms.
result ISR algorithms achieve provable domain generalization with fewer training environments.