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.

168,982 papers · 148 categories

Trend · papers per month

65130195260 · Jun 202019922001200920172026
48 results for self-supervised regularization

SinSim improves self-supervised learning by integrating optimal transport into contrastive learning.

problem Lack of explicit regularization in contrastive learning methods leads to suboptimal generalization.
method Integrates Sinkhorn regularization from optimal transport theory into SimCLR.
result SinSim outperforms SimCLR and other self-supervised methods on various datasets.

Self-supervised regularization improves semi-supervised learning performance without requiring unlabeled data.

problem Improving semi-supervised learning performance with limited labeled data.
method Introducing self-supervised regularization as a new approach to combine unlabeled data features.
result Self-supervised regularization significantly improves semi-supervised performance on image classification benchmarks.

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.

CurvSSL improves SSL by aligning local manifold curvature.

problem Improving self-supervised learning by capturing local manifold geometry.
method CurvSSL augments Barlow Twins with a curvature-based regularizer to align and decorrelate embeddings across augmentations.
result Curvature-regularized SSL yields competitive or improved linear evaluation performance.

Unified theory for representation learning using learnable functions.

problem Insufficient theoretical understanding of unsupervised and self-supervised learning.
method Discriminative theoretical framework for analyzing sample complexity.
result Learnable regularization functions can reduce the amount of labeled data needed.

Self-supervised learning performs better than supervised learning on imbalanced datasets.

problem The performance gap between balanced and imbalanced pre-training with self-supervised learning is smaller than with supervised learning.
method Systematic investigation of self-supervised learning under dataset imbalance, including experiments and theoretical analyses.
result Self-supervised representations are more robust to class imbalance than supervised representations.

GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the discriminator, which must perform classification under an (adversarially) shifting data distribution…

2018-10-27abs ↗pdf ↗

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.

Improves disentangled GAN training and selection without labeled data.

problem Challenges in training disentangled GANs, especially self-supervision.
method Contrastive Regularizer and ModelCentrality for unsupervised disentanglement.
result Significantly improved disentanglement scores without labeled data.

This study investigates self-supervised learning with Wasserstein distance on tree structures.

problem Improving self-supervised learning methods using Wasserstein distance.
method Utilized Tree-Wasserstein distance (TWD) and Jeffrey divergence regularization for training.
result A simple combination of softmax function and Tree-Wasserstein distance outperforms cosine similarity-based methods.

T-JEPA learns tabular data representations without augmentations, outperforming traditional methods.

problem Challenges in self-supervised learning for tabular data due to lack of data augmentations.
method T-JEPA uses a Joint Embedding Predictive Architecture (JEPA) to predict latent representations of different subsets of features within the same sample.
result Significant improvement in classification and regression tasks, outperforming traditional methods.

Proposes SSL framework for improving item recommendations in large-scale systems.

problem Sparse feedback data for long-tail items in recommender systems.
method Multi-task self-supervised learning framework with data augmentation.
result Significant improvements in model performance, especially on slices lacking supervision.

Paper tackles rDR classification and lesion segmentation using self-supervised equivariant learning and attention-based MIL.

problem Classifying rDR and segmenting lesions from image-level labels.
method Integrates self-supervised equivariant attention mechanism (SEAM) with attention-based multi-instance learning (MIL).
result Achieved AU ROC of 0.958 on Eyepacs dataset, outperforming state-of-the-art.

Maximizes image representation dependence for self-supervised learning.

problem Learning meaningful image representations from unlabeled data.
method Maximizes Hilbert-Schmidt Independence Criterion (HSIC) between image transformations and identity.
result Matches state-of-the-art performance on ImageNet and other vision tasks.

AaSP improves audio self-supervised learning by addressing aliasing issues.

problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.

C2^2VAE learns disentangled and coupled representations without prior knowledge.

problem Learning disentangled and coupled representations in latent space.
method Introduces C2^2VAE, a self-supervised VAE that factorizes posterior and uses Gaussian copula for dependencies.
result Demonstrates strong effect in enhancing disentangled representation learning.

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.

This work explains how maximizing latent correlations across multiple data views helps in identifying shared and private components.

problem Understanding how to identify shared and private components in multiview data.
method An intuitive generative model of multiview data is adopted, and latent correlation maximization is shown to guarantee the extraction of shared components.
result Latent correlation maximization guarantees the extraction of shared components across views and disentangles private information.

Paper proposes S2S^2ConvSCN for robust subspace clustering and classification.

problem Insufficient handling of nonlinear manifolds, data corruptions, and out-of-sample data.
method Self-supervised convolutional subspace clustering network (S2S^2ConvSCN) with FC layer, CIM for robustness, and BD regularization.
result Robust S2S^2ConvSCN outperforms baseline on unseen data.

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.

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.

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.

Survey of self-supervised learning methods in computer vision, NLP, and graph learning.

problem Manual labeling and vulnerability to attacks in supervised learning.
method Generative, contrastive, and generative-contrastive approaches.
result Self-supervised learning achieves high performance in representation learning.

Self-supervised attention model improves weakly labeled audio event classification.

problem Efficiently classify audio events with minimal labeled data.
method Develops a self-supervised attention model for weakly labeled audio clips.
result Self-supervised attention model performs comparably to strongly supervised model trained with strong labels.

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.

This paper analyzes self-supervised learning from a multi-view perspective.

problem Understanding and optimizing self-supervised learning from multi-view data.
method Information-theoretical framework to understand and design self-supervised learning objectives.
result Self-supervised representations can extract task-relevant information and discard task-irrelevant information.

Generative model explains self-supervised learning across various tasks.

problem Lack of theoretical understanding of self-supervised learning methods.
method Generative latent variable model for self-supervised learning.
result Improves representation learning performance and narrows the gap between generative and discriminative methods.

Paper tackles self-supervised learning for non-homophilous graphs.

problem Existing self-supervised learning methods assume homophilous graphs, but real-world graphs often lack this assumption.
method Develops a decoupled self-supervised learning (DSSL) framework that decouples different semantics between neighborhoods.
result DSSL framework achieves better performance on various graph benchmarks compared to competitive baselines.

New insights into how data transformations affect self-supervised clustering.

problem Impact of data transformations on self-supervised clustering convergence.
method Theoretical and empirical analysis of various data transformations.
result Certain transformations help in faster convergence of self-supervised clustering.

TopoGeoScore selects robust checkpoints using only source-domain representations.

problem Selecting robust checkpoints without target-domain labels or samples.
method Constructs class-conditional mutual k-nearest-neighbour graphs and extracts three interpretable signals.
result Source representations contain measurable global-local-topological evidence of robustness.

Improved self-supervised learning on ImageNet achieves top-1 accuracy of 77.1%.

problem Self-supervised ResNets underperform supervised learning on ImageNet.
method ReLICv2 combines explicit invariance loss with contrastive objective over varied data views.
result ReLICv2 achieves 77.1% top-1 accuracy on ImageNet, improving over previous state-of-the-art by 1.5%.

DM improves self-supervised transfer learning by matching target distributions.

problem Improving self-supervised transfer learning performance.
method Distribution Matching (DM) method that drives representation distribution towards a predefined reference distribution.
result DM outperforms existing methods on target classification tasks.

Unified framework improves deep multi-view clustering by addressing self-supervision and contrastive alignment issues.

problem Variations in self-supervision-based methods for deep multi-view clustering.
method Unified DeepMVC framework that includes recent methods and leverages self-supervision and contrastive alignment.
result Contrastive alignment negatively impacts cluster separability, especially with many views.