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.
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.
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.
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.
Theoretical analysis of data quality and synergies in LLMs.
problem Understanding why different training methods require different amounts of data.
method Theoretical analysis of transformers trained on a weight prediction task for linear regression.
result SFT excels on smaller datasets challenging for the pretrained model, while RL benefits from large, not overly difficult data.
Mask-reconstruction pretraining helps in downstream tasks by capturing more semantic features.
problem How mask-reconstruction pretraining helps in downstream tasks and why it surpasses supervised learning.
method Theoretical analysis and experimental validation of mask-reconstruction pretraining (MRP) on auto-encoders.
result MRP provably captures more semantic features than supervised learning, leading to better performance in downstream tasks.
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.
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.
This paper proves the theoretical advantage of unsupervised pretraining for machine learning tasks.
problem Understanding why unsupervised pretraining helps in machine learning tasks.
method A generic framework using Maximum Likelihood Estimation (MLE) for unsupervised pretraining and Empirical Risk Minimization (ERM) for downstream tasks.
result Proves an excess risk of i l d e O ( C Φ / m + C Ψ / n ) ilde{\mathcal{O}}(\sqrt{\mathcal{C}_Φ/m} + \sqrt{\mathcal{C}_Ψ/n}) i l d e O ( C Φ / m + C Ψ / n ) for downstream tasks under mild conditions. 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.
CLIP learns joint image-text representations for zero-shot learning.
problem Understanding and improving zero-shot transfer performance in CLIP.
method Formal study of transferrable representation learning and analysis of zero-shot transfer performance.
result Proposes a new CLIP-type approach that outperforms existing methods.
We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given masked-o…
End-to-end training solves deep unsupervised contrastive learning problems.
problem Theoretical analysis of unsupervised contrastive learning.
method End-to-end training of deep neural networks.
result Approximate stationary solutions found for non-convex contrastive loss.
Develops methods for training models with few annotations in computer vision tasks.
problem Training models with limited labeled data in computer vision.
method Theoretical, algorithmic, and experimental contributions for Meta-Learning and Semi-Supervised Learning.
result Improves Contrastive Learning and proposes a semi-supervised method for transformer-based object detectors.
Paper introduces a simple method to assign uncertainty in contrastive learning models.
problem Contrastive learning models lack uncertainty measures.
method Trains a deep network to assign uncertainty based on representation variance.
result Deep uncertainty model improves anomaly detection and out-of-distribution classification.
New statistical theory explains contrastive learning effectiveness.
problem Understanding why contrastive learning works well for representation extraction.
method Developed a new theoretical framework based on approximate sufficient statistics.
result Near-sufficient encoders derived from contrastive learning can be adapted for downstream tasks.
Transformers learn low-dimensional target functions efficiently in-context.
problem Efficiently learning nonlinear target functions in-context using transformers.
method Nonlinear MLP layer in transformers optimized by gradient descent, focusing on single-index target functions.
result Transformers can learn target functions with low-dimensional structures efficiently in-context.
This paper improves model training by using a reference model to guide target model training.
problem Improving generalization and data efficiency in model training.
method DRRho risk minimization framework based on Distributionally Robust Optimization (DRO).
result DRRho risk minimization improves generalization and data efficiency compared to training without a reference model.
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 ( ≤ \le ≤ 13 labeled images per class). 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.
Transformers learn to use induction heads or shortcuts based on data diversity.
problem How data diversity influences the behavior of transformers.
method Gradient-based training of a single-layer transformer on a minimal task.
result Data diversity steers transformers toward induction heads or shortcuts.
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.
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.
Framework adds invariance to pretrained networks without fine-tuning.
problem Adding invariance to pretrained networks without altering original behavior.
method Post-training augmentation invariance framework with Markov-Wasserstein minimization and Wasserstein correlation maximization losses.
result Adapter networks improve classification accuracy on rotated and noisy images.
Enhances contrastive learning for better representation learning on wild images.
problem Binary partition of views from same and different instances limits CL's performance.
method Doubly Contrastive Learning (CACR) with contrastive attraction and repulsion.
result CACR improves performance and robustness on wild image datasets.
The paper studies how search and distillation improve reasoning in large language models.
problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.
Task-agnostic data augmentation shows little benefit for pretrained transformers.
problem Evaluating the effectiveness of task-agnostic data augmentation on pretrained transformers.
method Conducted a systematic examination of two data augmentation techniques (Easy Data Augmentation and Back-Translation) across 5 tasks, 6 datasets, and 3 pretrained transformer models.
result Data augmentation techniques previously effective for non-pretrained models fail to consistently improve performance for pretrained transformers, even with limited training data.
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.
Enhances CLIP's similarity computation using PMI's linear structure.
problem CLIP's similarity computation misses the optimal linear structure of PMI.
method KME-CLIP, utilizing inner product in a reproducing kernel Hilbert space.
result KME-CLIP approximates PMI with arbitrary accuracy and outperforms CLIP.
Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.
problem Improving text classification accuracy with pretrained models.
method Examined the benefits of pretrained models on text classification tasks with varying amounts of training data.
result As the number of training examples grows into the millions, the accuracy gap between pretrained BERT-based models and vanilla LSTM narrows to within 1%.
New framework selects high-quality pretraining data without training LLMs.
problem Slow progress in understanding pretraining data due to costly experiments.
method Statistical framework based on perplexity-benchmark correlations.
result Approach outperforms existing methods on multiple benchmarks.
Paper studies how few pretraining tasks are needed for a linear model to solve new tasks.
problem How many pretraining tasks are needed for a linear model to solve new tasks?
method Pretrained a linear attention model for linear regression with a Gaussian prior.
result Effective pretraining requires a small number of independent tasks, and the model closely matches Bayes optimal.
Fine-grained pretraining improves neural network's ability to learn rare features.
problem Improving generalization in deep learning models.
method Introducing a hierarchical multi-view structure to confine input data distribution.
result Fine-grained pretraining leads to better accuracy on hard downstream test samples.
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
Paper introduces a multi-stage influence function to track model predictions.
problem Improving natural language processing and computer vision performance.
method Develops a multi-stage influence function to track predictions from finetuned models back to pretraining data.
result Identifies pretraining examples contributing most to finetuning task predictions.
Pretraining method enhances dialogue representation learning across various tasks.
problem Scarce labeled data for specific dialogue tasks.
method Multi-task unsupervised pretraining with natural training objectives.
result Significant improvement in downstream tasks without encoder discrimination.
Synthetic continued pretraining enhances model performance with synthetic data.
problem Data inefficiency in pretrained models when adapting to domain-specific documents.
method Synthetic data augmentation using EntiGraph to create a large synthetic corpus.
result Language models can answer questions and follow instructions without access to domain-specific documents.
WeatherFormer learns robust weather features from small datasets.
problem Modeling complex weather dynamics from limited data.
method Pretrained transformer encoder on large satellite dataset, with spatiotemporal encoding.
result State-of-the-art performance in county-level soybean yield prediction and influenza forecasting.
Denoised smoothing defends pretrained classifiers against adversarial attacks.
problem Adversarial attacks on pretrained classifiers.
method Prepending a denoiser to any off-the-shelf classifier using randomized smoothing.
result Guaranteed ℓ p \ell_p ℓ p -robustness to adversarial examples without modifying the pretrained classifier. Study shows uncertainty of deep learning models can be measured from their embeddings.
problem Uncertainty in contrastive learning models for critical applications.
method Estimating the distribution of training data in embedding space and accounting for local consistency.
result Uncertainty of an embedding vector correlates strongly with downstream accuracy.
Study shows how pretraining robustness transfers to downstream tasks.
problem Understanding how robustness is transferred from pretraining to downstream tasks.
method Theoretical analysis and practical validation of robustness constraints.
result Robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation.
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.
New research reveals how the pretraining distribution affects in-context learning in large language models.
problem Understanding how the pretraining distribution influences in-context learning in large language models.
method Developed a theoretical framework to characterize the relationship between pretraining distribution properties and in-context learning performance.
result Characterized a fundamental trade-off between robust task selection and generalization in ICL due to the pretraining distribution's statistical properties.
Research improves federated text models for next word prediction.
problem Training models on distributed devices efficiently and effectively.
method Employ transfer learning in federated learning for next word prediction.
result Enhancements to current baselines with pretrained embeddings and whole model pretraining.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
Publicly pretraining models on Web data may undermine differential privacy.
problem The use of large Web-scraped datasets in differential privacy models.
method Critical review of leveraging pretrained models on public datasets for differential privacy.
result Publicizing pretrained models as 'private' could harm trust and generalize poorly.
New study finds best language model architecture and pretraining objective for zero-shot tasks.
problem Evaluating which language model architectures and pretraining objectives best enable zero-shot generalization.
method Compared three model architectures and two pretraining objectives across 170 billion tokens, with and without finetuning.
result Causal decoder-only models trained on autoregressive language modeling exhibit strongest zero-shot generalization.