The study explores the strengths and weaknesses of models that generalize from weak to strong supervision.
problem Understanding the limitations and capabilities of models that generalize from weak to strong supervision.
method Theoretical analysis and experimental validation in both classification and regression settings.
result Theoretical bounds reveal the importance of strong generalization and calibration of the weak model and a careful balance in the training process.
RAVEN improves weak-to-strong generalization under distribution shifts.
problem Weak models fail to supervise strong models effectively under distribution shifts.
method RAVEN dynamically learns optimal combinations of weak models and strong model parameters.
result RAVEN outperforms existing methods by over 30% on out-of-distribution tasks.
New model shows weak teachers can help strong students learn even with imperfect labels.
problem Improving strong student's performance with weak teacher's imperfect pseudolabels.
method Stylized overparameterized spiked covariance model with Gaussian covariates, proving two phases of generalization.
result Provable successful and random guessing phases of strong student's generalization.
Weak labels can significantly speed up learning for strong tasks.
problem Learning with limited strong labels.
method Using weak labels to accelerate learning of strong tasks.
result Weak labels can accelerate learning to O(icefrac1n) rate. Weak supervision challenges black-box models, suggesting fusion of modeling cultures.
problem Challenges of strong supervision in achieving accurate predictions.
method Integrating data modeling into algorithmic modeling for weak supervision.
result Integration of data modeling culture improves model stability and accuracy.
We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attention is deployed to help a model distinguish between relevant and irrelevant parts …
This work explores how feature decorrelation improves self-supervised learning.
problem Complete and dimensional collapse issues in self-supervised learning.
method Study of a concise framework and connection to feature decorrelation.
result Feature decorrelation improves self-supervised learning.
New theory explains how strong models can learn from weak ones.
problem Learning from weak, incomplete, or incorrect labels.
method New bounds based on data distribution and student hypothesis class.
result Existing weak supervision theory fails to account for pseudolabel correction and coverage expansion.
Study shows how a strong model can learn a task's feature while retaining other capabilities.
problem How to align superhuman AI systems using weak-to-strong generalization.
method Two-layer neural networks, reward-model learning, multi-step SGD, feature learning.
result The strong model efficiently learns task features while retaining general capabilities.
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised mult…
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have shown the benefits of training on large unlabeled datasets, we find improvements in …
The effectiveness of supervised learning techniques has made them ubiquitous in research and practice. In high-dimensional settings, supervised learning commonly relies on dimensionality reduction to improve performance and identify the most important factors in predicting outcomes. However, the economic importance of …
Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced classification. So far, various supervised AUC optimization methods have been developed and they are also extended to semi-supervised scenarios to cope with small sample problems. However, existing semi-supe…
For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a projection of the supervised estimate onto a set of constraints imposed by the u…
C2VAE learns disentangled and coupled representations without prior knowledge.
problem Learning disentangled and coupled representations in latent space.
method Introduces C2VAE, a self-supervised VAE that factorizes posterior and uses Gaussian copula for dependencies. result Demonstrates strong effect in enhancing disentangled representation learning.
Study of multi-task semi-supervised learning in high dimensions.
problem Analysis of multi-task semi-supervised learning in high-dimensional settings.
method Random matrix theory applied to characterize asymptotics of key functionals.
result Predicts algorithm performance and provides efficient usage guidelines.
Human language is a rich multimodal signal consisting of spoken words, facial expressions, body gestures, and vocal intonations. Learning representations for these spoken utterances is a complex research problem due to the presence of multiple heterogeneous sources of information. Recent advances in multimodal learning…
APC overcomes missing data and class imbalance in time series data.
problem Missing data and class imbalance in time series data.
method Self-supervised learning with Autoregressive Predictive Coding (APC).
result APC improves classification performance on real-world medical datasets.
Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based on consistency regularization can harness the abundance of unlabeled data to pr…
Self-supervised skip-tree training improves mathematical reasoning in language models.
problem Improving logical reasoning in language models for formal mathematics.
method Self-supervised language modeling on mathematical formulas, skip-tree task.
result Models trained on skip-tree task outperform standard models in mathematical reasoning tasks.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
GANs can approximate SDEs for large time steps.
problem Approximating SDEs for large time steps using GANs.
method Proposed a conditional GAN architecture to enable strong approximation of SDEs.
result Supervised GAN outperformed standard GAN and other schemes in strong error.
Unified framework for semi-supervised learning reduces annotation needs.
problem Sparse annotations and large amounts of unlabeled data in computational pathology.
method S5CL integrates fully-supervised, self-supervised, and semi-supervised learning through hierarchical contrastive losses.
result S5CL improves accuracy and F1-score in histopathological datasets with sparse labels.
Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.
problem Denoising autoregressive signals corrupted by heavy-tailed noise.
method Self-supervised learning approach without requiring full noise distribution knowledge.
result Strong denoising performance compared to baseline methods, especially for impulsive noise.
Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closely related Dual Coordinate Ascent (DCA) method has been implemented in various software packages, it has so far lacked go…
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Althou…
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.
Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.
problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.
New measure quantifies contrastive self-supervised learning's generalization ability.
problem Limited theoretical understanding of contrastive self-supervised learning's generalization.
method Defined (σ,δ)-measure to mathematically quantify data augmentation and provide an upper bound for downstream classification error. result Generalization ability is related to alignment of positive samples, divergence of class centers, and concentration of augmented data.
Data mining methods have been widely applied in financial markets, with the purpose of providing suitable tools for prices forecasting and automatic trading. Particularly, learning methods aim to identify patterns in time series and, based on such patterns, to recommend buy/sell operations. The objective of this work i…
This paper proposes a novel kernel approach to linear dimension reduction for supervised learning. The purpose of the dimension reduction is to find directions in the input space to explain the output as effectively as possible. The proposed method uses an estimator for the gradient of regression function, based on the…
SPIN converts weak LLMs to strong ones using self-play.
problem Growing strong LLMs without human-annotated data.
method Self-play fine-tuning (SPIN) starting from a supervised fine-tuned model.
result SPIN significantly improves LLM performance across benchmarks.
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 (≤13 labeled images per class). DBT combines diffusion models and boosting for supervised learning.
problem Supervised learning problems.
method Diffusion Boosting paradigm and Diffusion Boosted Trees (DBT).
result DBT outperforms deep neural network-based diffusion models and is effective on real-world classification tasks.
New method identifies latent variables with sparse perturbations.
problem Identifying latent variables with minimal supervision.
method Weakly supervised representation learning with sparse perturbations.
result Identification of latent variables up to specified blocks.
New algorithm robustly trains deep neural networks under corrupted supervision.
problem Training deep neural networks with corrupted supervision data.
method Unified framework for classification and regression, focusing on collective impact of data points on average gradient.
result Achieves strong guarantees without assuming the type of corruption, robust under various types of corruption.
Fisheye cameras are commonly used in applications like autonomous driving and surveillance to provide a large field of view (>180∘). However, they come at the cost of strong non-linear distortions which require more complex algorithms. In this paper, we explore Euclidean distance estimation on fisheye cameras …
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harvested via these means, sometimes resulting in entire classes of data on which learn…
We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the pa…
Graph neural network executes value iteration for flexible environments.
problem Value iteration in flexible environments with direct supervision.
method Graph Neural Network (GNN) executing value iteration algorithm.
result GNN accurately models value iteration across diverse environments.
The paper cleans label noise in supervised classification using Bernoulli sampling.
problem Label noise degrades supervised classifier performance.
method Proposes a label noise cleaning method based on Bernoulli random sampling.
result The method separates clean and noisy observations without prior label information.
TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.
problem Robustness to label noise in weakly-supervised learning.
method TrustNet learns noise patterns from trusted data, then trains a robust classifier using these patterns.
result TrustNet outperforms state-of-the-art methods in robustness to various noise patterns.
ORDisCo learns from unlabeled data to improve semi-supervised continual learning.
problem Lack of effective use of unlabeled data in semi-supervised continual learning.
method Deep Online Replay with Discriminator Consistency (ORDisCo) that continually passes the learned data distribution to a classifier and selectively stabilizes discriminator parameters.
result Significant performance improvement on various semi-supervised learning benchmark datasets.
We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the frame…
We introduce a new approach for topic modeling that is supervised by survival analysis. Specifically, we build on recent work on unsupervised topic modeling with so-called anchor words by providing supervision through an elastic-net regularized Cox proportional hazards model. In short, an anchor word being present in a…
Foundation models outperform supervised methods in time series forecasting across various operational regimes.
problem Lack of domain-specific training and ongoing maintenance in supervised learning for time series forecasting.
method Evaluation of foundation models against standard supervised approaches across four operational regimes: periodic, physically constrained, stochastic, and demand forecasting.
result Foundation models are optimal for cold-start or long-tail scenarios and perform well in domains with transferable periodic structures.
Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not always possible (it depends on how useful, for inferring the labels, it would be …
New recursive algorithm estimates conditional kernel mean embeddings in Hilbert space.
problem Estimating conditional distributions in RKHS for supervised learning.
method Recursive algorithm in L2 space for conditional kernel mean map. result Strong L2 consistency of recursive estimator proved.