CF-VAE models capture multi-modal distributions for better structured sequence prediction.
problem Challenges in capturing multi-modality of future states in latent variable models.
method Conditional Flow Variational Autoencoders (CF-VAE) with conditional normalizing flows.
result CF-VAE achieves state-of-the-art results on multi-modal structured sequence prediction datasets.
This research tackles uncertainty estimation in autoregressive structured prediction tasks.
problem Ensuring safety and robustness of AI systems through accurate uncertainty estimation.
method Develops a unified probabilistic ensemble-based framework for token-level and sequence-level uncertainty estimation.
result Provides baselines for error and out-of-domain detection on translation and speech recognition datasets.
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…
PANDA predicts protein binding affinity changes from sequences, outperforming existing methods.
problem Accurately predicting changes in protein binding affinity due to mutations.
method Sequence-based machine learning approach using protein sequence information.
result PANDA achieves higher Pearson correlation coefficients than existing methods.
Inferring the structural properties of a protein from its amino acid sequence is a challenging yet important problem in biology. Structures are not known for the vast majority of protein sequences, but structure is critical for understanding function. Existing approaches for detecting structural similarity between prot…
Seq-SetNet processes sequence sets directly, improving protein structure prediction.
problem Processing sequence sets (MSAs) for structural inference without considering sequence order.
method Developed a symmetric function module to integrate features from MSAs.
result Seq-SetNet outperforms state-of-the-art approaches by 3.6% in precision.
Unsupervised framework learns symmetry from time sequences.
problem Learning symmetry from time sequences without labeled data.
method Meta-sequential prediction (MSP) framework that leverages stationary properties.
result Hidden disentangled structure emerges as a by-product of training.
Deep learning predicts protein structures accurately.
problem Predicting the 3D structure of proteins from amino acid sequences.
method Embeddings and deep learning models for backbone atom distance matrices and torsion angles.
result Competitive results in CASP13 and CASP12, surpassing previous winners.
GPT learns a causal world model from token predictions, validated in game sequences.
problem Does GPT implicitly learn a causal world model from token predictions?
method Derived a causal interpretation of GPT's attention mechanism and proposed zero-shot causal structure learning.
result GPT can generate legal next moves with high confidence for sequences with encoded causal structures, but fails for illegal moves.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in v…
Rapid progress in deep learning has spurred its application to bioinformatics problems including protein structure prediction and design. In classic machine learning problems like computer vision, progress has been driven by standardized data sets that facilitate fair assessment of new methods and lower the barrier to …
Two ML frameworks predict antibody properties using structural data.
problem Predicting antibody properties using sequence and structural data.
method ANTIPASTI and INFUSSE models using graph representations and neural networks.
result ANTIPASTI predicts binding affinity; INFUSSE predicts residue flexibility.
Predict human lives using sequences of life events.
problem Predicting human life outcomes based on detailed event sequences.
method Adapting natural language processing techniques to analyze life events.
result Models predict diverse outcomes with high accuracy, outperforming state-of-the-art models.
The folding structure of the DNA molecule combined with helper molecules, also referred to as the chromatin, is highly relevant for the functional properties of DNA. The chromatin structure is largely determined by the underlying primary DNA sequence, though the interaction is not yet fully understood. In this paper we…
Identification of high affinity drug-target interactions is a major research question in drug discovery. Proteins are generally represented by their structures or sequences. However, structures are available only for a small subset of biomolecules and sequence similarity is not always correlated with functional similar…
Generative Link Sequence Modeling predicts future links in evolving networks.
problem Predicting future links in networks with evolving structures.
method Sequence modeling framework with self-tokenization to capture temporal link formation patterns.
result GLSM achieves best performance on AUC metrics compared to existing methods.
Safe Pattern Pruning reduces pattern explosion in predictive pattern mining.
problem Exponential growth of patterns in structured data.
method Safe Pattern Pruning (SPP) method.
result Effective model building in practical data analysis.
Predicting RNA base distances using a large language model.
problem Accurately predicting RNA structural information, especially distance maps.
method Using a large pretrained RNA language model coupled with a transformer.
result The model can accurately infer RNA base distances from sequence data.
Set-Sequence model learns cross-sectional dynamics directly from time series data.
problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.
A new transformer model uses Monte Carlo methods for sequence prediction.
problem Predicting sequences from observations with uncertainty.
method Integrates Monte Carlo methods into a transformer architecture to model stochastic sequences.
result Proposes a generative model with predictive distributions.
The study explores how Transformers predict the next token in a sequence.
problem Understanding the mechanism behind Transformers' autoregressive learning ability.
method Exploring the approximation ability of Transformers for next-token prediction through specific instances and a causal kernel descent method.
result Transformer models can learn context-dependent functions f for next-token prediction based on past and current observations. Bayesian context trees capture complex dependencies in categorical sequences.
problem Complex, long-range dependencies in categorical sequences are not well captured by simple models.
method Parsimonious Bayesian context trees with model-based agglomerative clustering for efficient inference.
result The proposed framework outperforms existing models on real-world data.
GNL addresses dynamic network regression by learning dynamic graph structures and capturing sequence information.
problem Dynamic network regression of multiple inter-connected data entities.
method Graph Neural Lasso (GNL) using gated diffusive units and attention mechanism.
result GNL outperforms existing methods in dynamic network regression tasks.
Transformers can predict pseudo-random sequences from LCGs with unseen parameters and moduli.
problem Learning pseudo-random number sequences from linear congruential generators with unknown parameters and moduli.
method Investigated the ability of Transformers to learn LCG sequences with varying complexity and moduli. Analyzed embedding layers and attention patterns.
result Transformers can predict pseudo-random sequences from LCGs with unseen parameters and moduli, up to mexttest=216, using a two-step strategy. Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design architectures to suit it. As such, architectures that fit the structure of genomics should …
Motivation. Protein contact map describes the pairwise spatial and functional relationship of residues in a protein and contains key information for protein 3D structure prediction. Although studied extensively, it remains very challenging to predict contact map using only sequence information. Most existing methods pr…
Mathematical framework for language models processes text and predicts next tokens.
problem Understanding and optimizing the performance of large language models.
method Describes encoding, prediction models, learning from data, and deployment of LLMs.
result Demonstrates remarkable empirical successes and provides a platform for further research.
SENSE enhances node sequences in graphs using vector embeddings.
problem Efficiently capturing graph node sequences for applications.
method SENSE-S learns node embeddings and composes them for sequences, preserving node order.
result SENSE-S increases multi-label classification and link-prediction accuracy by up to 50% and 78% respectively.
PLUS pre-trains protein sequences with structural info, improving performance.
problem Lack of labeled protein sequences for training models.
method PLUS combines masked language modeling with same-family prediction for pre-training.
result PLUS-RNN outperforms other models in protein biology tasks.
Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This manuscript presents Deep Convolutional Neural Fields (DeepCNF), a combination of DCNN with Conditional Random Field (CRF), for sequence labeling with highly imbalanced label distribution. The widely-us…
THP model captures complex dependencies in event sequences efficiently.
problem Inability of existing models to capture long-term dependencies in event sequences.
method Transformer Hawkes Process (THP) model using self-attention mechanism.
result THP outperforms existing models in likelihood and event prediction accuracy.
Predicts node sequences in graphs using multi-order network models.
problem Predicting sequences of node traversals in graphs.
method Combines multiple higher-order network models into a multi-order model, fitting and selecting the optimal maximum order.
result Outperforms state-of-the-art algorithms for next-element and full sequence prediction.
Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning …
A system is presented that segments, clusters and predicts musical audio in an unsupervised manner, adjusting the number of (timbre) clusters instantaneously to the audio input. A sequence learning algorithm adapts its structure to a dynamically changing clustering tree. The flow of the system is as follows: 1) segment…
Deep learning models forecast stock market orders over multiple time frames.
problem Forecasting stock market orders over varying time frames.
method Encoder-decoder models with sequence-to-sequence and Attention mechanisms, leveraging Intelligent Processing Units (IPUs) for faster training.
result Multi-horizon forecasting outperforms single-horizon models, especially for long prediction periods.
We propose a framework for general probabilistic multi-step time series regression. Specifically, we exploit the expressiveness and temporal nature of Sequence-to-Sequence Neural Networks (e.g. recurrent and convolutional structures), the nonparametric nature of Quantile Regression and the efficiency of Direct Multi-Ho…
Study Thompson Sampling in adversarial bit prediction, finding regret bounds and optimal sequences.
problem Adversarial bit prediction with varying error weights.
method Thompson Sampling, analyzing sequences with largest and smallest regret.
result Regret bounds for adversarial bit prediction sequences, including optimal and worst-case scenarios.
ATS2S model predicts RUL of industrial equipment using attention mechanism.
problem Accurate estimation of RUL for industrial equipment to improve maintenance schedules and reduce costs.
method ATS2S model that optimizes reconstruction and RUL prediction losses, uses attention mechanism, and integrates encoder and decoder features.
result ATS2S model achieves superior performance over 13 state-of-the-art methods on four real datasets.
New techniques improve channel prediction in noisy wireless systems.
problem Predicting channels in wireless communication systems from noisy observations.
method Adapted sequence-to-sequence models and transformers with reverse positional encoding and reversed encoder outputs.
result Improved robustness and relationship capture in channel prediction models.
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem and answer, as well as raise, questions about integrating structures for induct…
Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that …
Symmetric CNNs improve sequential recommendation and protein structure prediction.
problem Improving prediction accuracy in sequential recommendation and protein structure inference.
method Developed a CNN architecture that preserves symmetry in convolutional layers, using parameterized convolutional kernels.
result Symmetric structured CNNs achieve better performance with fewer parameters.
New method uses Cantor embeddings and Wasserstein distances to analyze predictive states in time series data.
problem Analyzing predictive states in stochastic processes using time series data.
method Wasserstein distances for detecting predictive equivalences in symbolic data, using Cantor embeddings for finite-dimensional representation.
result Exploratory analysis of temporal structure in various processes reveals insights.
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to …
As high-throughput biological sequencing becomes faster and cheaper, the need to extract useful information from sequencing becomes ever more paramount, often limited by low-throughput experimental characterizations. For proteins, accurate prediction of their functions directly from their primary amino-acid sequences h…
Meta-learning improves event prediction from short sequences.
problem Predicting events from short sequences is challenging.
method Meta-learning approach using recurrent neural networks and monotonic neural networks.
result Meta-learning enhances long-term prediction performance.
This research proves guarantees on sequence models' generalization to longer and novel sequences.
problem Generalization to longer sequences and novel token combinations in sequence models.
method Provable guarantees on length and compositional generalization for various sequence models.
result Limited capacity models achieve both length and compositional generalization with diverse training distributions.
New L2D framework allows deferring specific parts of a sequence prediction to experts.
problem Current L2D methods defer entire predictions, which is not ideal for long sequences.
method Proposes token-level and one-time rejectors to defer specific outputs of a model prediction to experts.
result Granular deferrals achieve better cost-accuracy tradeoffs than whole deferrals.