A new approach to protein language models combines latent space prediction with masked language modeling.
problem Improving protein language models by predicting amino acid identities at masked positions.
method A variant of masked language modeling that predicts latent targets only at masked positions, retaining the MLM cross-entropy.
result The new approach outperforms pure masked language modeling on 11 out of 16 downstream tasks.
The Minimal Learning Machine (MLM) is a nonlinear supervised approach based on learning a linear mapping between distance matrices computed in the input and output data spaces, where distances are calculated using a subset of points called reference points. Its simple formulation has attracted several recent works on e…
Pretrained masked language models (MLMs) require finetuning for most NLP tasks. Instead, we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are computed by masking tokens one by one. We show that PLLs outperform scores from autoregressive language models like GPT-2 in a variety of task…
Introduces MLM dataset for multitask learning across multiple languages and modalities.
problem Training and evaluating multitask systems on diverse data.
method Develops a new benchmark dataset with semantic data and modalities.
result Demonstrates challenges in generalizing on diverse data.
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%.
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
New neural network models speed up Bayesian multilevel modeling.
problem Complex computational challenges in Bayesian multilevel modeling.
method Probabilistic neural network architectures that leverage multilevel model factorization.
result Efficient posterior inference on unseen datasets with near-instant results.
Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve based mod…
GP-TS optimizes TLM pre-training hyperparameters efficiently.
problem Resource inefficiency in TLM pre-training.
method Bayesian optimization with Thompson sampling and Gaussian process.
result GP-TS achieves lower MLM loss in fewer epochs.
Expands MLM by masking token positions, improving performance and convergence.
problem Improving language model performance and convergence.
method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.
result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.
Accelerates MCMC sampling for large-scale problems using machine learning.
problem Efficiently sampling large-scale Bayesian inference problems with high computational cost.
method Integrates low-fidelity machine learning models into a multilevel MCMC framework.
result Significantly accelerates multilevel sampling by a factor of two with similar accuracy.
Transformers' self-attention mechanism is mapped to a generalized Potts model.
problem Uncertainty in what type of data distribution self-attention can efficiently learn.
method Decouple word positions and embeddings, then show self-attention learns a generalized Potts model.
result Training self-attention is equivalent to solving the inverse Potts problem.
Enhances explainability of AI models without sacrificing accuracy.
problem Lack of interpretability in black-box models like Deep Neural Networks and Gradient Boosting.
method Co-supervised Local Model Synthesis (SynthTree) using Mixture of Linear Models (MLM).
result Statistical models significantly enhance explainability of AI models.
Downscaled models outperform larger ones on GLUE tasks.
problem Difficulty in attributing performance changes to specific factors in large language models.
method Pre-trained down-scaled versions of Transformer-based architectures on a common corpus, benchmarked on GLUE tasks.
result MLM + NSP (BERT-style) consistently outperforms other objectives.
Transformers exhibit abrupt learning in matrix completion tasks.
problem Understanding abrupt learning in Transformers for matrix completion.
method Formulated matrix completion as MLM task, trained BERT model, analyzed model components.
result Sudden drop in loss despite no changes in training procedure or hyper-parameters.
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
problem Understanding the statistical underpinnings of bidirectional attention.
method Exploring bidirectional attention as a mixture-of-experts model and reparameterizing it.
result Bidirectional attention can be viewed as a continuous bag of words model with mixture-of-experts weights.