arXiv research

Study improves Bayesian optimisation with ensemble transfer learning.

The paper improves classification accuracy by leveraging a shared signal across domains in high-dimensional classification.

A new GNN architecture called coVariance neural network (VNN) improves stability and transferability of covariance matrix analysis.

Proposes a transfer learning method for PCA studies.

Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer across models. We hypothesize that adversarial weakness is composed of three sources of bias: architecture, dataset, and random initialization.…

PCA-based MTL improves performance with reduced computation.

TL-PCA uses transfer learning to improve PCA performance with limited target data.

Transfer knowledge from multiple sources to improve matrix completion.

Transfer learning improves MNI's performance in high-dimensional linear regression.

The paper proposes reusable network components by making them compatible across tasks.

Bayesian model transfers knowledge across different engineering fleets.

Study improves model fit by transferring info from related datasets.

Vision transformers benefit from non-smooth components in adaptation.

UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world applications. A neural network pretrained on large datasets, such as ImageNet, can signifi…

Training on mixed distributions improves test performance even when components are unrelated.

FinEAS models financial sentiment using BERT embeddings.

New model improves transfer learning and semi-supervised learning.

New method UADs improves transferability of adversarial perturbations.

Proves Riemannian positive mass theorem with singularities.

In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. I…

The paper tackles transfer learning for growing matrix representations, improving estimation accuracy.

This paper improves MI-based BCIs by applying transfer learning across all components.

New framework explains fast transfer of hyperparameters across model scales.

VNNs transfer well across datasets for brain age prediction using cortical thickness features.

We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of methods has been proposed for vectorial data onl…

Mathematical framework for transfer learning feasibility and transfer risk.

Paper evaluates membership inference attacks on transfer learning models.

Enhances FDA for robust, efficient federated learning.

The paper analyzes phase transitions in transfer learning for perceptrons.

This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing met…

In terms of transfer entropy, we investigated the strength and the direction of information transfer in the US stock market. Through the directionality of the information transfer, the more influential company between the correlated ones can be found and also the market leading companies are selected. Our entropy analy…

We extend the theoretical analysis of a recently proposed single subspace learning algorithm, called Dual Principal Component Pursuit (DPCP), to the case where the data are drawn from of a union of hyperplanes. To gain insight into the properties of the $\ell_1$ non-convex problem associated with DPCP, we develop a geo…

TX-Ray analyzes and quantifies model knowledge transfer in NLP.

Enhancing spectral embedding for low-dimensional embeddings in rare disease cohorts

G5 universal GRAPH-BERT learns graph representations across different datasets.

When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task. However, when transferring knowledge from a less related source, it may inversely hurt the target performance, a phenomenon known as negative transfer. Despite its p…

Proposes a transfer learning method for high-dimensional quantile regression.

TabSurv adapts tabular neural networks for survival analysis.

Introduce a thermodynamically informed, temperature-transferable MLCG framework for proteins.

Study shows benefits of transfer learning with neural networks.

Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper…

Variational auto-encoder frameworks have demonstrated success in reducing complex nonlinear dynamics in molecular simulation to a single non-linear embedding. In this work, we illustrate how this non-linear latent embedding can be used as a collective variable for enhanced sampling, and present a simple modification th…

Optimal feature transfer identified through bias-variance analysis.

This paper proposes a TL method for SOH estimation of lithium-ion batteries.

DRUM transfers cardiac arrest models across registries with missing covariates.

Paper proposes a method to combine multiple facial analysis models for better performance.

We analyze a simple asset transfer model in which the transfer amount is a fixed fraction $f$ of the giver's wealth. The model is analyzed in a new way by Laplace transforming the master equation, solving it analytically and numerically for the steady-state distribution, and exploring the solutions for various values o…