Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

246492738984 · Jun 202019922001200920182026
48 results for unlabelled networks

New method uses unlabelled data to improve Bayesian Neural Networks.

problem Lack of ability to use unlabelled data in conventional Bayesian Neural Networks.
method Self-supervised Bayesian Neural Networks using contrastive pretraining and variational lower bound optimization.
result Prior predictive distributions capture problem semantics better and improve predictive performance.

This paper uses unlabeled data to improve compressed neural networks.

problem Difficulty in retraining pre-trained models due to limited labeled data.
method Uses unlabeled data to mimic classification characteristics and aligns feature distributions using adversarial loss.
result Unlabeled data significantly improves the performance of compressed neural networks.

GPNs use unlabeled data to estimate uncertainty in Bayesian problems.

problem Limited training data in high-dimensional problems.
method Generative Posterior Networks (GPNs) that approximate the posterior distribution using unlabeled data.
result GPNs improve epistemic uncertainty estimation and scalability.

TAP transfers knowledge from unlabeled data to improve cross-modal learning.

problem Improving supervised learning performance using unlabeled data from a different modality.
method Probabilistic approach for missing information estimation, kernel regression, cross-attention module, TAP neural network.
result TAP significantly improves generalization across different domains and neural network architectures.

Paper proposes a reinforcement learning approach to learn classifiers from positive and unlabeled data.

problem Learning binary classifiers from positive and unlabeled data without prior class prior or label noise estimation.
method Alternately trains a policy network and a classifier using reinforcement learning, adapting label assumptions for unlabeled data.
result Significant improvement in classification performance compared to existing methods.

Generative Adversarial Positive-Unlabeled Learning tackles binary PU data classification.

problem Overfitting in conventional PU models with limited positive data.
method Innovative generative adversarial framework with multiple discriminators and generators.
result GenPU framework can recover both positive and negative data distributions at equilibrium.

SEGCN uses a student-teacher framework to improve GCN's performance on semi-supervised learning.

problem GCN's limitation in utilizing unlabeled data effectively.
method SEGCN combines GCN with Mean Teacher to leverage unlabeled nodes.
result SEGCN significantly improves classification accuracy on semi-supervised learning tasks.

Proposes a few-shot learning method for feature selection without labeled data.

problem Feature selection in unlabeled data with limited instances.
method Uses Concrete random variables and permutation-invariant neural networks to select features from multiple source tasks.
result Outperforms existing methods in feature selection performance.

The paper characterizes averages of unlabeled networks and their asymptotic behavior.

problem Developing network-based analogues of basic tools for scalar and vector data.
method Characterizing a space of unlabeled, undirected networks, describing its topological and geometric properties, and using these to establish asymptotic behavior of empirical means.
result Asymptotic behavior of a generalized notion of an empirical mean under sampling from a distribution supported on the space of unlabeled networks.

New CNNs learn features from unlabeled data for better activity recognition.

problem Limited labeled data for activity recognition leads to poor generalization.
method Semi-supervised CNNs that learn features from raw sensor data.
result Semi-supervised CNNs outperform supervised and traditional methods by up to 18%.

Paper proposes a progressive ensemble network for zero-shot image recognition.

problem Challenges of zero-shot learning due to lack of labeled data and expanding categories.
method Proposes a progressive ensemble network with multiple projected label embeddings.
result Demonstrates improved zero-shot image recognition performance on multiple datasets.

Study shows adding unlabelled data improves semi-supervised image segmentation accuracy.

problem Improving semi-supervised image segmentation accuracy with limited labelled data.
method Investigated the impact of varying labelled and unlabelled data quantities in a semi-supervised segmentation algorithm.
result Significantly higher segmentation accuracy achieved with semi-supervised approach compared to supervised learning.

Neural approach for Chinese word segmentation using lexicon and unlabeled data.

problem Efficiently segment Chinese words with limited labeled data.
method Posterior regularization algorithm with indirect supervision from lexicon and unlabeled data.
result Validation of approach on multiple benchmark datasets in in-domain and cross-domain scenarios.

Unified analysis of self-training for deep networks on unlabeled data.

problem Theoretical understanding of self-training for deep networks on unlabeled data.
method Unified theoretical analysis using expansion assumption and input-consistency regularization.
result Proves high accuracy of minimizers of population objectives based on self-training and input-consistency regularization.

Enhances few-shot image classification using unlabelled examples.

problem Few-shot image classification with limited labeled data.
method Transductive meta-learning combining soft k-means clustering and neural feature extractor.
result State-of-the-art performance on Meta-Dataset, mini-ImageNet, and tiered-ImageNet benchmarks.

Paper shows using unlabeled mismatched images can improve KD for image classification.

problem Improving Knowledge Distillation for image classification with limited labeled data.
method Used unlabeled mismatched images as stimulus for KD, focusing on stimulus complexity.
result Stimulus complexity is crucial for KD's effectiveness, as demonstrated on MNIST and CIFAR datasets.

New method uses unlabeled data to prevent forgetting in deep learning.

problem Catastrophic forgetting in lifelong learning with deep neural networks.
method Class-incremental learning scheme with global distillation, confidence-based sampling, and learning strategy.
result Significantly higher accuracy and less forgetting compared to state-of-the-art methods.

DEDPUL improves PU learning by estimating proportions and classifying unlabeled data.

problem Analog to supervised binary classification with only positive samples clean and unlabeled mixtures of positive and negative.
method Applies a post-processing procedure to any classifier trained to distinguish positive and unlabeled data, estimating proportions alongside classification.
result Outperforms state-of-the-art in both proportion estimation and PU classification.

Novel algorithm estimates local permutations in unlabeled multi-view sensing.

problem Estimating local permutations in unlabeled multi-view sensing.
method Graph alignment and Gromov-Wasserstein alignment exploiting multiple views.
result The proposed algorithm is scalable and applicable to challenging SNR regimes.

ORDisCo learns from unlabeled data to improve semi-supervised continual learning.

problem Lack of effective use of unlabeled data in semi-supervised continual learning.
method Deep Online Replay with Discriminator Consistency (ORDisCo) that continually passes the learned data distribution to a classifier and selectively stabilizes discriminator parameters.
result Significant performance improvement on various semi-supervised learning benchmark datasets.

ClusterNet uses few labeled data and unlabeled data to improve clustering performance.

problem Limited performance of current clustering approaches due to lack of labeled data and unsupervised learning limitations.
method ClusterNet employs pairwise semantic constraints from a small set of labeled data and utilizes abundant unlabeled data. It defines a new loss function combining semantic similarity and constrained k-means clustering.
result ClusterNet achieves superior clustering performance on various datasets compared to state-of-the-art deep clustering methods.

Improved emotional speech classification using deep learning.

problem Difficult to assess subtle emotional changes in speech.
method Deep Convolutional Generative Adversarial Networks (DCGAN) for unlabeled data, multitask learning.
result Speaker-independent classification performance improved to 43.88% on a 5-point scale and 49.80% on a 3-point scale.

Improves writer identification with unlabeled data and weighted label smoothing.

problem Offline writer identification requires labeled data, which is costly and time-consuming.
method Proposed a semi-supervised feature learning pipeline with weighted label smoothing regularization.
result Significantly improved baseline performance on writer identification datasets.

Paper proposes a new softmax loss for better performance in Positive and Unlabeled data tasks.

problem Current softmax losses and sampling schemes have drawbacks in Positive and Unlabeled learning.
method Proposes Relaxed Softmax (RS) loss and a new negative sampling scheme.
result New training objective drives uplifts in performance on textual and recommendation datasets.

This paper proposes a new method to use unlabeled data as positive data, improving PU learning.

problem Improving positive-unlabeled learning methods in deep learning.
method Labeling large-loss unlabeled data as positive data and developing a new learning objective.
result The proposed method outperforms the latest importance reweighting method in experiments.

Method improves regression models using unlabeled data.

problem Improving predictive performance of regression models with limited labeled data.
method Mixed semi-supervised generalized-linear-regression with different mixing mechanisms.
result Integrating unlabeled data consistently improves predictive performance.

Integrates competitive learning into CNNs to enhance representation and speed up fine-tuning.

problem Efficient use of unlabeled data for CNNs' fine-tuning.
method Integrates unsupervised competitive learning into the convolutional layer of CNNs.
result Effective representation learning using unlabeled data, accelerated fine-tuning process.

SDORE uses neural networks to estimate regression functions and their gradients, even with limited labeled data.

problem Nonparametric estimation of regression functions and their gradients.
method Semi-supervised deep ReQU neural networks with gradient norm regularization.
result Achieves minimax optimal convergence rates in L2L^{2}-norm and plug-in gradient estimator convergence.

Big models pretrain and fine-tune for semi-supervised learning on ImageNet.

problem Learning from few labeled examples with a large amount of unlabeled data.
method Unsupervised pretraining of a big ResNet model followed by supervised fine-tuning and distillation.
result 73.9% ImageNet top-1 accuracy with just 1% of labels (\le13 labeled images per class).

Safe semi-supervised learning for SPNs improves performance without degrading.

problem Expensive class annotations and abundant unlabelled data.
method Semi-supervised parameter learning for Sum-Product Networks (SPNs) that guarantees safe learning.
result SPNs can improve generative and discriminative objectives without degrading performance.

ACL improves robustness with unlabeled data, and we analyze its generalization using Rademacher complexity.

problem Improving robustness of deep networks against adversarial attacks using unlabeled data.
method We analyze the generalization performance of Adversarial Contrastive Learning (ACL) using Rademacher complexity.
result The average adversarial risk of the downstream tasks can be upper bounded by the adversarial unsupervised risk of the upstream task.

Topaz uses neural networks to pick particles from cryoEM images efficiently.

problem Manual particle picking is time-consuming and requires post-processing.
method Positive-Unlabeled (PU) learning with minimal labeled data.
result Topaz improves cryoEM reconstruction resolution by up to 0.15 Å.