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.

168,932 papers · 148 categories

Trend · papers per month

0.7%1.3%2.0%2.6% · May 202619922001200920172026
48 results for self-supervised pretraining

This study compares transfer learning and self-supervised learning for better model performance.

problem Choosing between transfer learning and self-supervised learning for optimal model performance.
method Comprehensive comparative study of transfer learning and self-supervised learning under various data and task properties.
result Self-supervised learning outperforms transfer learning in certain applications, and vice versa.

CERT improves language understanding by contrastively learning sentence-level semantics.

problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.

TAPE benchmarks protein learning tasks, finds self-supervised pretraining boosts performance.

problem Fragmented datasets and lack of standardized evaluation in protein modeling.
method TAPE introduces five semi-supervised learning tasks, curates splits, benchmarks models.
result Self-supervised pretraining more than doubles performance in some cases.

Paper analyzes self-supervised learning using causal methods and proposes a new objective.

problem Lack of theoretical understanding of self-supervised learning success.
method Uses a causal framework to enforce invariance constraints on proxy classifiers.
result ReLIC objective improves generalization guarantees and outperforms existing methods.

PULSE learns representations from physiological time series.

problem Lack of effective pretraining objectives for physiological time series.
method Proposes a pretraining framework exploiting dynamical systems generative model.
result PULSE learns representations that distinguish semantic classes and improve transfer learning.

Self-supervised method detects replay spoofing using acoustic configurations.

problem Challenges in collecting large-scale datasets for replay spoofing detection.
method Self-supervised pretraining of acoustic configurations using existing datasets.
result The method outperforms baseline by 30% on ASVspoof 2019 physical access dataset.

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.

A method for self-supervised learning of multivariate time series data across varying channels.

problem Labeling multivariate biomedical time series data is laborious and expensive.
method Proposes a multi-view self-supervised learning approach using a message passing neural network to extract a single representation across channels.
result Our method, combined with the TS2Vec loss, outperforms all other methods in most settings.

Researchers propose a new SSL risk decomposition method to evaluate and improve self-supervised learning models.

problem Self-supervised learning evaluation is limited to a single metric, providing little insight into model performance and improvement.
method Proposes an SSL risk decomposition that considers four error components: approximation, representation usability, probe generalization, and encoder generalization.
result Analysis of 169 SSL vision models reveals the main sources of error and provides insights for improving SSL models in specific settings.

This work improves adaptive conformal prediction using self-supervised learning.

problem Improving the adaptability of conformal prediction intervals.
method Train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores.
result Empirically demonstrates the benefit of additional information in improving the efficiency (width), deficit, and excess of conformal prediction intervals.

Two CSSL-based methods improve graph classification with limited labeled data.

problem Limited labeled data for graph classification leads to overfitting.
method Contrastive self-supervised learning (CSSL) for graph encoders pretraining and regularization.
result CSSL methods reduce overfitting and improve graph classification accuracy.

Flaky performance found in GNN SSL on RDBs, leading to worse linear evaluation.

problem Downstream task performances of GNN SSL on RDBs are poor.
method Proposed InfoNode to maximize mutual information between initial and final node representations.
result InfoNode improves GNN SSL performance on RDBs, supporting conjecture of conflict between SSL and GNN message passing.

Study evaluates self-supervised representations in interactive environments.

problem Unclear which self-supervised methods best capture meaningful features of diverse environments.
method Quantitative evaluation of representations in two visual environments: Flappy Bird and Sonic The Hedgehog.
result Representations' utility depends on the visuals and dynamics of the environment.

Unsupervised method discovers interpretable directions in GAN latent space.

problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.

New method improves self-supervised representation learning using probabilistic modeling and Monte Carlo integration.

problem Improving self-supervised representation learning for multimodal data.
method Discriminative probabilistic modeling with multiple importance sampling (MIS) for robust Monte Carlo integration.
result Proposes a novel non-parametric method for approximating conditional probability densities through convex optimization.

A self-supervised debiasing method using rank regularization mitigates spurious correlations in neural networks.

problem Spurious correlations cause biases in deep neural networks, affecting generalization.
method Spectral analysis of latent representations, rank regularization, self-supervised pretraining, debiasing of downstream tasks.
result The proposed framework significantly improves generalization performance and outperforms supervised debiasing approaches.

Theoretical study on how model architecture affects contrastive learning performance.

problem Understanding the role of model architecture in self-supervised learning.
method Theoretical analysis of contrastive learning, focusing on model capacity and clustering structures.
result Contrastive representations have lower dimensionality than the number of clusters in the data distribution.

Self-supervised learning improves ECG classification performance.

problem Label scarcity in clinical 12-lead ECG data.
method Adapted self-supervised methods to ECG domain, focusing on contrastive representations and latent forecasting.
result Contrastive predictive coding adaptation yields linear evaluation performance only 0.5% below supervised performance.

Selfie pretrains image embeddings without pixel-level predictions.

problem Training image embeddings efficiently with limited labeled data.
method Contrastive Predictive Coding loss for masked patches, using convolutional and attention mechanisms.
result Significant improvement in ResNet-50 accuracy on ImageNet 224 x 224 with 60 examples per class (5%).

A new mutual information optimization method using self-supervised binary contrastive learning.

problem Improving self-supervised contrastive learning for better model performance.
method Proposes a novel loss function for contrastive learning that optimizes mutual information in positive and negative pairs.
result The proposed method outperforms state-of-the-art self-supervised contrastive frameworks on various benchmark datasets.

Physen-Noise2Noise tackles defocus deblurring in low-light conditions with physics-guided self-supervised learning.

problem Defocus deblurring in low-light conditions with complex biased noise.
method Physics-guided self-supervised deblurring framework that leverages noisy multi-frame observations and a learnable noise bias parameter.
result Physen-Noise2Noise consistently outperforms state-of-the-art methods in defocus deblurring with complex biased noise.

New bounds for contrastive learning handle domain shifts and generalization.

problem Domain shifts and generalization challenges in downstream tasks.
method Novel generalization bounds accounting for both domain shift and generalization.
result Performance of contrastively learned representations depends on statistical discrepancy between pretraining and downstream distributions.

This work analyzes the role of data augmentation in self-supervised learning using RKHS approximation and regression.

problem Limited theoretical understanding of the role of data augmentation in self-supervised learning.
method Geometric characterization of the target function given by augmentation, proving generalization bounds.
result Two generalization bounds are derived, one free of model complexity, the other specific to near-optimal encoders.

Paper analyzes why deeper layers of ViTs perform worse on out-of-distribution tasks.

problem Performance degradation of intermediate layers in ViTs under distribution shift.
method Extensive linear probing experiments across various benchmarks and fine-grained analysis of transformer modules.
result Probing feedforward network activations yields best performance under significant distribution shift.

DiffDenoise preserves fine structures in medical images using conditional diffusion models.

problem Medical image denoising often results in loss of fine structures.
method Conditional diffusion model with stabilized reverse sampling and supervised training.
result DiffDenoise outperforms state-of-the-art methods in medical image denoising.

This paper improves anomaly detection in lane rendering images for safer navigation.

problem Anomalies in lane rendering images can mislead drivers, posing safety risks.
method Proposes a four-phase pipeline using Transformer models, self-supervised pre-training, and fine-tuning.
result The pipeline enhances detection accuracy and reduces training time.

Geometric theory of projection heads in self-supervised learning.

problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.

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).

Self-supervised learning from unlabeled sensor data improves model performance in federated learning.

problem Lack of labeled data in decentralized IoT devices.
method Wavelet transform and contrastive learning for self-supervised feature extraction.
result Self-supervised features achieve strong performance and generalize well in federated learning.

LeJEPA provides a scalable, theory-driven approach to self-supervised learning.

problem Lack of practical guidance and theory in JEPAs.
method Identified optimal Gaussian distribution and introduced SIGReg objective.
result LeJEPA achieves state-of-the-art performance with minimal hyperparameters and heuristics.

The dissertation establishes a contexture theory to mathematically characterize representation learning.

problem The lack of a scientific understanding of representation learning in foundation models.
method Introduces the contexture theory as a unified framework for analyzing representation learning methods.
result Representation learning is optimal when the association between input and context is neither too strong nor too weak.

This dissertation automates deep learning pipelines and uses meta-learning for better model selection and data augmentation.

problem Challenges in selecting and fine-tuning deep learning pipelines for new datasets.
method Meta-learning for DL pipeline selection and data augmentation, using synthetic data.
result Meta-learned approaches outperform traditional methods in automated DL pipeline selection and data augmentation.

S4 learns new self-supervision automatically, improving accuracy with less human effort.

problem Lack of direct supervision in machine learning.
method Combines deep learning and probabilistic logic to automatically generate and verify new self-supervision.
result S4 can automatically propose accurate self-supervision, matching supervised methods with less human effort.

BigBiGAN improves unsupervised representation learning using image generation quality.

problem Improving unsupervised representation learning methods.
method Extending BigGAN to include an encoder and modifying the discriminator for representation learning.
result BigBiGAN models achieve state-of-the-art performance in unsupervised representation learning and unconditional image generation.

Self-supervised learning excels in topic modeling by being less model-specific.

problem How self-supervised learning discovers useful representations in topic models.
method Applying self-supervised learning objectives to topic model-generated data.
result Self-supervised learning objectives can recover useful posterior information for topic models, outperforming misspecified models.