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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “Self-Ensembling”

Domain Confusion with Self Ensembling for Unsupervised Adaptationcs.LG

DCSE combines domain confusion and self-ensembling for unsupervised adaptation.

problem Unsupervised domain adaptation with time-consuming data collection and annotation.

method DCSE combines domain confusion and self-ensembling to learn invariant representations.

result DCSE outperforms existing methods in various unsupervised domain adaptation benchmarks.

unsupervised adaptation domain confusion self-ensembling invariant representation

2018-10-10abs ↗pdf ↗

Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Spacecs.LG

This work improves SSL by leveraging disentangled latent space for better self-ensembling.

problem Improving semi-supervised learning performance with limited labeled data.

method Stacked SSL model using unsupervised disentangled representation learning for stochastic embedding.

result Improved performance and interpretability of disentangled representations over related SSL models.

semi-supervised learning disentangled latent space self-ensembling stochastic embedding chest X-ray images

2019-07-22abs ↗pdf ↗

Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemblecs.LG

Enhances robustness for time series classification using self-ensemble method.

problem Limited adversarial robustness in time series classification.

method Proposes a self-ensemble method to improve Randomized Smoothing's robustness certification.

result Demonstrates superior robustness compared to baseline approaches.

time series classification adversarial robustness Randomized Smoothing self-ensemble certified robustness

2024-09-04abs ↗pdf ↗

Smooth Neighbors on Teacher Graphs for Semi-supervised Learningcs.LG

SNTG improves semi-supervised learning by considering data connections.

problem Improving semi-supervised learning performance with fewer labeled data.

method Constructs a graph from teacher model predictions and learns smooth representations of similar neighboring points.

result Achieves state-of-the-art results on semi-supervised learning benchmarks.

semi-supervised learning graph-based smoothness teacher model self-ensembling

2017-11-01abs ↗pdf ↗

SELF: Learning to Filter Noisy Labels with Self-Ensemblingcs.CV

SELF filters noisy labels to improve deep learning performance.

problem Overfitting to noisy labels in deep learning.

method Self-ensemble label filtering (SELF) using running averages of predictions.

result SELF improves task performance by filtering noisy labels dynamically.

deep learning noisy labels self-ensemble filtering semi-supervised learning

2019-10-04abs ↗pdf ↗

Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learningcs.LG

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.

Graph Convolutional Networks Semi-Supervised Learning Self-Ensembling Mean Teacher GCN

2018-09-26abs ↗pdf ↗

Towards Robust Neural Networks via Random Self-ensemblecs.LG

New defense algorithm RSE improves neural network robustness against adversarial attacks.

problem Vulnerability of deep neural networks to small adversarial perturbations.

method Combines randomness and ensemble techniques to add noise layers and ensemble predictions.

result Significantly outperforms previous defense techniques, maintaining high accuracy under strong attacks.

neural networks adversarial attacks robustness ensemble randomness

2017-12-02abs ↗pdf ↗

Self-Ensemble Protection: Training Checkpoints Are Good Data Protectorscs.LG

SEP uses checkpoints to protect data from training good models.

problem Protecting data from competitors training high-performance models.

method Forming perturbed examples using model checkpoints' gradients to ensure they are always unrecognized.

result SEP significantly reduces model accuracy when trained on perturbed data, demonstrating its effectiveness.

data protection model checkpoints deep learning ensemble protection imperceptible perturbations

2022-11-22abs ↗pdf ↗

A Domain Adaptive Density Clustering Algorithm for Data with Varying Density Distributioncs.LG

DADC algorithm improves clustering for data with varying density.

problem Sparse cluster loss and cluster fragmentation in density peak clustering.

method Domain-adaptive density measurement, cluster center self-identification, and cluster self-ensemble.

result DADC achieves more reasonable clustering results on data with varying density.

density clustering sparse clusters cluster fragmentation domain-adaptive K-Nearest Neighbors

2019-11-23abs ↗pdf ↗

Mantis: Lightweight Foundation Model for Time Series Classificationcs.LG

Mantis improves time series classification using a transformer model trained on synthetic data.

problem Insufficient application of foundation models to time series classification.

method Pre-trained transformer model on synthetic data, enhanced test-time methodology.

result Mantis achieves state-of-the-art performance across diverse datasets.

time series classification foundation models transformers synthetic data self-supervised learning

2025-02-21abs ↗pdf ↗

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcs.LG

Improved neural network robustness against adversarial attacks.

problem Adversarial attacks on neural networks.

method Adversarial-trained Bayesian Neural Network (Adv-BNN).

result State-of-the-art performance improvement under strong attacks.

Adversarial attacks Bayesian Neural Network Robustness Neural Networks Machine Learning

2018-10-01abs ↗pdf ↗

Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercs.LG

FedDST trains sparse sub-networks to improve efficiency in federated learning.

problem Efficiently train large models on resource-limited edge devices with limited network bandwidth.

method Dynamic sparse training to reduce model size and communication.

result FedDST outperforms existing methods in federated learning, especially in non-i.i.d. settings.

federated learning sparse training edge computing communication efficiency machine learning

2021-12-18abs ↗pdf ↗