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.
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.
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.
Simple method disentangles content and style from pre-trained vision models.
problem Learning interpretable features in visual representations.
method Probabilistic linear entanglement model and simple disentanglement algorithm.
result Method provably disentangles content and style features.
MeLa learns task relations by inferring global labels for robust FSL.
problem Few-shot learning with limited global labels.
method Meta Label Learning (MeLa) and augmented pre-training.
result MeLa outperforms existing methods across diverse benchmarks.
Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to variou…
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of downstream tasks. Along with continuous significant performance improvement, the size an…
Pre-training on different modalities improves Transformer performance in offline reinforcement learning.
problem Improving Transformer-based models for offline reinforcement learning tasks.
method Empirical investigation of pre-training on language and vision data, analysis of internal representations, and fine-tuning with no context.
result Pre-trained Transformers with language data can utilize context-like information to solve reinforcement learning tasks efficiently.
New findings on representation changes in transfer learning.
problem Understanding representation changes in transfer learning.
method Analysis of pre-trained and fine-tuned representations in transfer learning.
result Representation changes mainly occur in the head, but early layers are also important for cross-domain adaptation.
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
We investigate the effects of the unsupervised pre-training method under the perspective of information theory. If the input distribution displays multiple views of the supervision, then unsupervised pre-training allows to learn hierarchical representation which communicates these views across layers, while disentangli…
Paper develops a theory explaining contrastive pre-training for multimodal AI.
problem Limited theoretical understanding of contrastive pre-training for multi-modal AI.
method Introduces approximate sufficient statistics and Joint Generative Hierarchical Model.
result Near-minimizers of contrastive loss are approximately sufficient, enabling diverse downstream tasks.
Next basket recommendation, which aims to predict the next a few items that a user most probably purchases given his historical transactions, plays a vital role in market basket analysis. From the viewpoint of item, an item could be purchased by different users together with different items, for different reasons. Ther…
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
Paper proposes a method to learn linear regression models using multiple pre-trained models.
problem Learning a linear regression model with limited target data.
method Representation transfer learning method using multiple pre-trained models.
result The method achieves better sample complexity compared to baseline methods.
Paper proposes a unified time series forecasting model with adaptive transfer.
problem General forecasting models for diverse time series data.
method Unified representations through Decomposed Frequency Learning and adaptive domain-specific features via Time Series Register.
result State-of-the-art forecasting performance on seven real-world benchmarks.
Theoretical study shows adversarial training improves robustness in deep learning models.
problem Ensuring robustness in pre-trained deep learning models.
method Theoretical analysis of adversarial training and feature purification in two-layer neural networks.
result Adversarial training leads to feature purification, making models more robust to attacks.
Offline RL with pre-trained features amplifies errors even under mild shifts.
problem Sample-efficient offline RL with pre-trained features under mild distribution shift.
method Empirical study of offline RL with pre-trained neural representations.
result Substantial error amplification occurs even with pre-trained features, requiring stronger conditions for successful offline RL.
In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) are calculated through rule-based algorithms that map molecules to a sparse discrete space. However,…
Contrastive Code Representation Learning improves code summarization and type inference.
problem Code representations are sensitive to edits, hindering downstream semantic understanding tasks.
method ContraCode: a contrastive pre-training task that learns code functionality.
result Contrastive pre-training improves code summarization and type inference accuracy.
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with a language representation model pre-trained on multi-lingual corp…
EigenNoise provides a competitive word vector initialization scheme without pre-training data.
problem Improving word vector initialization without pre-training data.
method EigenNoise uses a dense, independent co-occurrence model to initialize word vectors.
result EigenNoise can approach GloVe performance without pre-training data.
Unsupervised pre-training improves model generalization, but lacks theoretical understanding.
problem Lack of theoretical understanding of unsupervised pre-training's impact on model generalization.
method Introduces a novel theoretical framework to analyze and enhance generalization.
result Enhances understanding of unsupervised pre-training and fine-tuning, proposing a new regularization method.
VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.
problem Lack of interpretability in existing time-series models.
method Vector quantization of time-series data into abstracted shapes.
result VQShape achieves comparable performance to specialist models in classification tasks.
We propose a novel learning method for multilayered neural networks which uses feedforward supervisory signal and associates classification of a new input with that of pre-trained input. The proposed method effectively uses rich input information in the earlier layer for robust leaning and revising internal representat…
New framework minimizes model complexity for improved few-shot learning.
problem Empirical benefits of pre-training scale with data size but lack theoretical explanation.
method Complexity Minimization framework for meta-representation learning.
result Theoretical analysis shows error rate improves with more meta-training data.
The study uses pre-trained neural networks to adjust for confounding in non-tabular data.
problem Neglecting non-tabular data sources can lead to biased ATE estimates.
method Leverages latent features from pre-trained neural networks to adjust for confounding.
result Neural networks can achieve fast convergence rates for ATE estimation with latent features.
New measure assesses time series pre-training data quality without labels.
problem Challenges in collecting diverse pre-training datasets for time series classification.
method Contrastive-learning-based foundation model and contrastive accuracy measure.
result Contrastive accuracy correlates with model performance on downstream tasks.
Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To…
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…
Optimus pre-trains sentences in a latent space for various NLP tasks.
problem Training large-scale language models for diverse NLP tasks.
method Pre-trained Variational Autoencoder (VAE) on large text corpus, fine-tuned for various tasks.
result Optimus achieves state-of-the-art on VAE language modeling benchmarks.
GEFA predicts drug-target affinity using graph neural networks.
problem Accurate prediction of drug-target interactions for rapid drug repurposing.
method GEFA (Graph Early Fusion Affinity) is a novel graph-in-graph neural network with attention mechanism.
result GEFA effectively models drug-target interactions, demonstrating the effectiveness of pre-trained protein embedding and nested graph representation.
SimCLR pre-training improves CNN performance with fewer labels.
problem Learning with fewer labeled data.
method SimCLR contrastive learning method combined with supervised fine-tuning.
result SimCLR pre-training with supervised fine-tuning achieves almost optimal test loss with fewer labeled data.
Paper improves Tm prediction of protein fragments using sparsity and probabilistic models.
problem Improving accuracy of melting temperature prediction for protein fragments.
method Promoting sparsity in pre-trained transformer models and adopting probabilistic frameworks.
result Mean absolute error of 0.23C for predicting melting temperature.
Paper introduces TS-GPT for engineering time series forecasting.
problem Engineering time series require causal operations, unlike linguistic data.
method Innovations representation theory, Generative Pre-trained Transformer.
result TS-GPT effectively forecasts real-time locational marginal prices.
Proposes using gradients as features for efficient deep learning adaptation.
problem Efficient deep representation learning for different tasks.
method Designs a linear model incorporating gradients and activations of a pre-trained network.
result Shows strong results across various tasks and datasets.
Deep Reinforcement Learning (DRL) algorithms are known to be data inefficient. One reason is that a DRL agent learns both the feature and the policy tabula rasa. Integrating prior knowledge into DRL algorithms is one way to improve learning efficiency since it helps to build helpful representations. In this work, we co…
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.
Kronos improves financial time series analysis with a pre-trained model.
problem Limited application of large-scale models to financial candlestick data.
method Unified, scalable pre-training framework for financial K-line modeling.
result Kronos excels in financial tasks like price forecasting and volatility prediction.
Paper proposes a new method for learning business process representations.
problem Challenges in capturing all useful information in business process data.
method Combines Gramian Angular Fields and Convolutional Neural Networks for representation learning.
result Demonstrates effectiveness of the approach through visualization and multiple process prediction tasks.
Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate prediction uncertainty in a pre-trained neural network model. Our method estimates the tr…
Study finds CLIP's caption-based learning outperforms image-only methods under certain conditions.
problem Comparing CLIP's performance with traditional image-only methods in learning transferable representations.
method Controlled comparison of CLIP and image-only methods using a dataset with descriptive captions and specific criteria.
result CLIP's caption-based learning outperforms image-only methods when certain conditions are met, but can be detrimental in others.
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.
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 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.
Simplified image clustering achieves competitive results without text-based embeddings.
problem Complexity and resource requirements of state-of-the-art clustering methods.
method SCP: trains a small cluster head using pre-trained vision model features and positive data pairs.
result SCP achieves highly competitive performance on various benchmark datasets.
lamBERT learns language and actions using multimodal BERT.
problem Learning language and actions in complex environments.
method Extending BERT to multimodal representation and integrating with reinforcement learning.
result lamBERT model achieved higher rewards in multitask and transfer settings.
TCGPN improves stock forecasting by capturing temporal correlation patterns.
problem Stock forecasting with minimal periodicity and large node numbers.
method TCGPN uses Temporal-Correlation fusion encoder and pre-training methods to handle large datasets.
result TCGPN achieves state-of-the-art results on real stock market data.