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.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “self-ensembling”

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 ↗

Domain Confusion with Self Ensembling for Unsupervised Adaptationcs.LG

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways to achieve this goal: adversarial learning and self training. In this article, …

2018-10-10abs ↗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 ↗

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 ↗

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

The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding perturbations to each single data point, while ignoring the connections between data…

2017-11-01abs ↗pdf ↗

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

Graph convolutional network (GCN) provides a powerful means for graph-based semi-supervised tasks. However, as a localized first-order approximation of spectral graph convolution, the classic GCN can not take full advantage of unlabeled data, especially when the unlabeled node is far from labeled ones. To capitalize on…

2018-09-26abs ↗pdf ↗

Towards Robust Neural Networks via Random Self-ensemblecs.LG

Recent studies have revealed the vulnerability of deep neural networks: A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural network misclassify. This makes it unsafe to apply neural networks in security-critical applications. In this paper, we propose a new defense…

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

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the la…

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 ↗