Survey on self-supervised pre-training for neural networks using unlabeled data.
problem Improving model performance using unlabeled data.
method Pre-training on unlabeled data followed by task-specific adaptation.
result Enhanced model performance through self-supervised pre-training.
Improved self-supervised learning for document images.
problem Performance of self-supervised pre-training on document images is poor.
method Proposed context-aware alternatives and a novel multi-modal method.
result Novel method outperforms other self-supervised methods on document image classification.
This paper connects masked pre-training to Bayesian model selection.
problem Understanding the success of masked pre-training and its generalization.
method The paper shows masked pre-training corresponds to maximizing the marginal likelihood.
result Masked pre-training with a suitable scoring function maximizes the marginal likelihood.
The paper develops an asymptotic theory of self-supervised pre-training.
problem Sharpness of current rates in self-supervised pre-training and their accuracy.
method Two-stage M-estimation and tools from Riemannian geometry.
result Characterization of the limiting distribution of the downstream test risk.
GPT-GNN pre-trains GNNs on unlabeled graphs to improve downstream performance.
problem Training GNNs requires labeled data, which is expensive.
method Generative pre-training of GNNs on unlabeled data with self-supervision.
result GPT-GNN significantly outperforms state-of-the-art GNNs without pre-training.
Self-supervised learning improves few-shot classification and segmentation on point clouds.
problem Efficiently learn from limited labeled data in point cloud applications.
method Hierarchical cover-tree partitioning for self-supervised pre-training; restricted to support set for few-shot learning.
result Self-supervised learning significantly improves downstream classification and segmentation accuracy.
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.
Improved pre-trained embeddings through effective entropy maximization.
problem Developing high-quality pre-trained embeddings for future tasks.
method E2MC criterion defined in terms of low-dimensional constraints.
result Significant improvement in downstream performance.
Self-supervised learning improves RUL prediction with limited data in fatigue damage prognosis.
problem Limited labelled data for RUL prediction in fatigue damage prognosis.
method Pre-training deep learning models on unlabelled sensor data using self-supervised learning.
result Self-supervised pre-trained models significantly outperform non-pre-trained models in RUL prediction with scarce labelled data.
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.
Improved conversion rate prediction in online advertising using self-supervised pre-training.
problem Data sparsity and calibration issues in predicting conversions given clicks.
method Self-supervised pre-training on all conversion events to enrich CVR prediction model without compromising calibration.
result Improvements in offline training and online A/B tests, with full deployment to Yahoo native advertising system.
Deep nearest neighbors outperform self-supervised methods in anomaly detection.
problem Anomaly detection using self-supervised deep methods.
method Simple nearest-neighbor approach on Imagenet pretrained features.
result Nearest-neighbor method outperforms self-supervised methods in accuracy, few shot generalization, training time, and noise robustness.
ProtoTransfer learns from unlabeled data to classify unseen tasks.
problem Few-shot classification with limited labeled data.
method Self-supervised prototypical transfer learning.
result ProtoTransfer outperforms unsupervised meta-learning methods.
Sketch-BERT learns vector sketches using BERT-like self-supervised learning.
problem Lack of effective vector sketch representation for recognition and retrieval tasks.
method Generalized BERT to sketch domain with novel embedding networks and self-supervised sketch gestalt learning.
result Improved performance on sketch recognition, retrieval, and gestalt tasks.
SidAE combines autoencoders and Siamese networks for self-supervised feature extraction.
problem Efficiently extract meaningful features from unlabeled data.
method Proposes SidAE, a combination of autoencoders and Siamese networks for self-supervised image classification.
result SidAE outperforms self-supervised baselines across multiple datasets and scenarios, especially with limited labeled data.
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.
Self-supervised learning helps train deep features without needing lots of labeled data.
problem Annotation bottleneck in deep learning.
method Four main families of self-supervised approaches applied to various data modalities.
result Self-supervised methods can now rival fully supervised pre-training across multiple data types.
Whole MILC learns brain disorder dynamics from unlabeled data.
problem Learning spatio-temporal brain disorder dynamics from unlabeled data.
method Self-supervised pre-training of whole MILC on unlabeled healthy control data.
result Whole MILC outperforms existing methods and provides diagnostic insights.
SuNCEt accelerates contrastive learning with minimal labeled data.
problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.
Paper proposes a hybrid loss function for graph self-supervised learning.
problem Improving self-supervised representation learning for graphs.
method Hybrid loss function combining VICReg and HSIC.
result Hybrid loss function outperformed other methods in 4 out of 7 cases.
TabDPT combines ICL and self-supervised learning to train tabular models on real data.
problem Slow generalization of tabular foundation models to unseen datasets.
method In-Context Learning (ICL) combined with self-supervised learning, using real data for pre-training.
result TabDPT achieves strong performance on regression and classification benchmarks.
SAINT improves neural networks for tabular data with row attention and contrastive pre-training.
problem Tabular data challenges in machine learning applications.
method SAINT combines row and column attention with contrastive self-supervised pre-training.
result SAINT outperforms previous deep learning methods and even gradient boosting methods on benchmark tasks.
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to this challenge is to pre-train a model on related tasks where data is abundant, and…
GCC pre-trains graph neural networks to transfer across diverse datasets.
problem Non-transferable graph models trained for specific datasets.
method Graph Contrastive Coding (GCC) framework using contrastive learning.
result GCC pre-trained models achieve competitive performance across multiple datasets.
Improved 3D MRI classification using contrastive learning with continuous proxy metadata.
problem Insufficient labelled data for 3D medical image classification.
method Proposed a new loss function (y-Aware InfoNCE) to leverage continuous proxy metadata in contrastive learning.
result 3D CNN model pre-trained on 10^4 multi-site healthy brain MRI scans outperforms fully-supervised methods.
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.
New approach uses contrastive learning for better wireless power control.
problem Improving power control in wireless networks.
method A multi-layer perceptron with a contrastive learning backbone and head.
result Significant gains in sum-throughput and sample efficiency over supervised learning.
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.
Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data, which is resource intensive and time consuming. Recent progress in self-supervised …
Novel bio-inspired masking for robust speech emotion recognition.
problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.
MARGE learns to reconstruct text by paraphrasing, achieving strong performance across multiple tasks.
problem Training sequence-to-sequence models with limited supervision.
method Unsupervised multi-lingual multi-document paraphrasing objective.
result Strong zero-shot performance on document translation and various tasks in multiple languages.
New approach uses prior knowledge to improve neural network representations.
problem Difficulty in learning robust internal representations without a large training set.
method Incorporates prior information into a pre-trained reasoning module.
result Improves representation learning in diverse self-supervised learning settings.
CLOCS uses contrastive learning to improve cardiac signal representations.
problem Lack of labelled data in cardiac signal analysis.
method Contrastive learning across space, time, and patients.
result CLOCS outperforms state-of-the-art methods and achieves strong generalization.
Constructing a dataset for replay spoofing detection requires a physical process of playing an utterance and re-recording it, presenting a challenge to the collection of large-scale datasets. In this study, we propose a self-supervised framework for pretraining acoustic configurations using datasets published for other…
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.
SATNet solves the Symbol Grounding Problem, enabling self-supervised learning.
problem Mapping visual inputs to symbolic variables without explicit supervision.
method Self-supervised pre-training pipeline and proofreading method.
result SATNet achieves full accuracy with no label leakage, surpassing state-of-the-art.
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.
Graph-based approach repairs programs from diagnostic feedback.
problem Learning to repair programs from limited labeled data and compiler error messages.
method Introduces program-feedback graph and graph neural network for reasoning, and self-supervised learning with unlabeled programs.
result DrRepair significantly outperforms prior work, achieving high repair rates.
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.
Generalizes adversarial learning for better latent variable inference in GANs.
problem Improving latent variable inference in GANs for diverse applications.
method Adversarial learning with multiple feedback layers, self-supervision, and auxiliary tasks.
result Achieves global optimum matching multiple joint distributions.
SFAVEL distills features from language models for fact verification without annotations.
problem Fact verification with semantically meaningful and compact features.
method Self-supervised pretraining using contrastive loss with language models.
result Achieved state-of-the-art results on FB15k-237 and FEVER.
As a mental disorder progresses, it may affect brain structure, but brain function expressed in brain dynamics is affected much earlier. Capturing the moment when brain dynamics express the disorder is crucial for early diagnosis. The traditional approach to this problem via training classifiers either proceeds from ha…
Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised learning tasks such as object classification and semantic segmentation. While mas…
Theory explains how AI models can predict unseen tasks without labeled data.
problem Understanding how AI models can generalize to unseen tasks.
method Developed a theoretical framework to analyze zero-shot prediction.
result Identified key quantities and independence relationships for generalization.
SLiCE learns contextual node embeddings for link prediction in heterogeneous networks.
problem Link prediction requires specific contextual information not captured by static node embeddings.
method Self-supervised pre-training with localized attention mechanisms.
result SLiCE significantly outperforms existing methods on link prediction tasks.
Study shows imbalanced labels can be beneficial but not always in class-imbalanced learning.
problem Challenges in class-imbalanced learning with heavy label bias.
method Systematic investigation of semi-supervised and self-supervised approaches to leverage imbalanced labels.
result Imbalanced labels are valuable in semi-supervised learning but not always in self-supervised learning.
Clarifies contributions of model architectures and resources in SOTA language models.
problem Difficulty in disentangling contributions of model architectures and resources.
method Overview of large pre-trained language models, focusing on their use of new architectures and resources.
result Identifies potential starting points for benchmark comparisons and areas for improvement.
Foundational brain dynamics model using stochastic optimal control.
problem Complex and noisy fMRI signals in brain dynamics.
method Continuous-discrete state space model with amortized inference and locally linear approximations.
result State-of-the-art results across various downstream tasks.