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.
Improved embeddings by topic-sensitive attention on large corpora.
problem Capturing sense of words in limited corpora using pretrained embeddings.
method Topic-sensitive attention on large topic-rich corpora to correct sense drift in pretrained embeddings.
result Limited corpus augmentation is more effective than adapting pretrained embeddings.
Selfie pretrains image embeddings without pixel-level predictions.
problem Training image embeddings efficiently with limited labeled data.
method Contrastive Predictive Coding loss for masked patches, using convolutional and attention mechanisms.
result Significant improvement in ResNet-50 accuracy on ImageNet 224 x 224 with 60 examples per class (5%).
MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.
problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.
New method for black-box adversarial attacks using pretrained model embeddings.
problem Efficiently attacking unknown target networks with high-level semantic patterns.
method Learn a low-dimensional embedding using a pretrained model, then search within the embedding space.
result Significant reduction in the number of queries for black-box adversarial attacks.
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.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
SEMASIA provides a large dataset of latent representations for model comparison.
problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.
Improves retrieval accuracy for hierarchical documents, especially for distant matches.
problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.
A new method uses a frozen language model to improve sample efficiency in reinforcement learning.
problem Improving sample efficiency in reinforcement learning with partially observable environments.
method FROZEN Hopfield network and HELM (History Embedding Language Model) method.
result HELM achieves new state-of-the-art results on Minigrid and Procgen environments.
PanRep learns universal node embeddings for heterogeneous graphs.
problem Learning universal node embeddings for heterogeneous graphs.
method Graph Neural Network (GNN) model with four decoders capturing different properties.
result PanRep outperforms unsupervised and supervised methods in node classification and link prediction.
URL benchmark evaluates uncertainty quantification in pretrained models.
problem Need for reliable uncertainty estimates in transferable pretrained models.
method Proposes URL benchmark to measure transferability of representations and uncertainty estimates.
result Transferable uncertainty quantification remains challenging but not contradictory to traditional goals.
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
TAPE benchmarks protein learning tasks, finds self-supervised pretraining boosts performance.
problem Fragmented datasets and lack of standardized evaluation in protein modeling.
method TAPE introduces five semi-supervised learning tasks, curates splits, benchmarks models.
result Self-supervised pretraining more than doubles performance in some cases.
NewsNet-SDF uses deep learning to integrate financial news with financial data for better asset pricing.
problem Combining unstructured text with structured financial data for accurate asset pricing.
method Adversarial networks and pretrained language model embeddings.
result Substantially outperforms alternatives with a Sharpe ratio of 2.80.
Debiasing techniques can worsen gender bias in text classification, but a tweak improves both.
problem Debiasing techniques can inadvertently increase gender bias in text classification.
method Investigated traditional debiasing techniques and found they worsen bias. Suggested a minor adjustment.
result A minor adjustment to debiasing techniques can reduce gender bias while maintaining high classification accuracy.
Several popular graph embedding techniques for representation learning and dimensionality reduction rely on performing computationally expensive eigendecompositions to derive a nonlinear transformation of the input data space. The resulting eigenvectors encode the embedding coordinates for the training samples only, an…
Click through rate (CTR) prediction is very important for Native advertisement but also hard as there is no direct query intent. In this paper we propose a large-scale event embedding scheme to encode the each user browsing event by training a Siamese network with weak supervision on the users' consecutive events. The …
We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
Algorithm adapts pretrained semantic segmentation models to new domains.
problem Adapting pretrained models to new, unlabeled domains without source data.
method Learn prototypical distribution in embedding space, align target domain with source domain.
result Method achieves competitive performance on benchmark tasks.
New analysis shows optimal embedding learning rate depends on vocabulary size, not just model width.
problem Optimal learning rate for language model embeddings is not well understood, especially with large vocabularies.
method Theoretical analysis of training dynamics, interpolation between μ μ μ P and LV regimes. result Optimal embedding learning rate scales as Θ ( w i d t h ) Θ(\sqrt{width}) Θ ( w i d t h ) in the LV regime, not Θ ( w i d t h ) Θ(width) Θ ( w i d t h ) as μ μ μ P predicts. Adapts pretrained models to new classes without additional training.
problem Training models on limited labels and predicting new, unseen classes.
method Uses Fréchet mean instead of argmax for prediction, leveraging metric space distances.
result Improves model performance on unseen classes by up to 29.7% on ImageNet.
Hi-RES framework extracts medical relations from articles and EHRs.
problem Manual annotation bottleneck in relation extraction.
method Labeling sentences, creating improved negative samples, using pretrained language models, and combining EHR embeddings.
result Significant accuracy increases in relation extraction, up to 0.998 for disorder-location relations.
Transformer model pretrains on synthetic graphs for AD detection.
problem Limited labeled data and class imbalance in AD diagnosis.
method Diffusion-generated synthetic graphs, Graph Transformers, transfer learning.
result Framework outperforms baselines in AD diagnosis metrics.
Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional features in vision. However, these approaches usually transfer unary features and largely ignore more stru…
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 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.
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%.
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.
LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.
problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.
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.
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.
Study examines biases in clinical word embeddings, revealing performance gaps across groups.
problem Biases in clinical word embeddings leading to performance differences across groups.
method Pretrained BERT models on MIMIC-III, fill-in-the-blank method, fairness evaluation on clinical tasks.
result Classifiers trained from BERT representations exhibit statistically significant differences in performance across groups.
We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main enhancement subnetwork. Second, we scale the number of noise environments presen…
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.
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.
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. Accelerates pulsar light curve inference with learned representations and optimization.
problem Computational expense of Markov chain Monte Carlo methods for posterior inference.
method Combining U-Net latent representations with local simulator-guided optimization.
result 120x reduction in inference time (24 hours to 12 minutes) with accuracy preserved.
Paper proposes a new graph neural network for task-independent graph embeddings.
problem Task-dependent embeddings in graph learning domains.
method Incorporates a novel graph neural network and rich Graph Kernels for unsupervised and supervised learning.
result Consistently outperforms existing models by 3% - 8% on graph classification benchmarks.
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.
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.