Related papers: Modular Deep Learning for Multivariate Time-Series…
We present a nonparametric Bayesian joint model for multivariate continuous and categorical variables, with the intention of developing a flexible engine for multiple imputation of missing values. The model fuses Dirichlet process mixtures…
Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…
Time series imputation models have traditionally been developed using complete datasets with artificial masking patterns to simulate missing values. However, in real-world infrastructure monitoring, practitioners often encounter datasets…
Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…
Dealing with missing values and incomplete time series is a labor-intensive, tedious, inevitable task when handling data coming from real-world applications. Effective spatio-temporal representations would allow imputation methods to…
In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…
Time series forecasting presents significant challenges in real-world applications across various domains. Building upon the decomposition of the time series, we enhance the architecture of machine learning models for better multivariate…
Deep learning (DL) approaches are being increasingly used for time-series forecasting, with many efforts devoted to designing complex DL models. Recent studies have shown that the DL success is often attributed to effective data…
Objective: The proper handling of missing values is critical to delivering reliable estimates and decisions, especially in high-stakes fields such as clinical research. The increasing diversity and complexity of data have led many…
Healthcare time series data is vital for monitoring patient activity but often contains noise and missing values due to various reasons such as sensor errors or data interruptions. Imputation, i.e., filling in the missing values, is a…
Real-time decoding of target variables from multiple simultaneously recorded neural time-series modalities, such as discrete spiking activity and continuous field potentials, is important across various neuroscience applications. However, a…
Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective…
There are significant benefits to serve deep learning models from relational databases. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system…
Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaReTS, a novel…
Accurate interpolation of seismic data is crucial for improving the quality of imaging and interpretation. In recent years, deep learning models such as U-Net and generative adversarial networks have been widely applied to seismic data…
Missing values are prevalent across various fields, posing challenges for training and deploying predictive models. In this context, imputation is a common practice, driven by the hope that accurate imputations will enhance predictions.…
As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current data management strategies face substantial challenges in…
In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of using exogenous variables in enhancing the prediction of the…
Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series…
Time series foundation models excel at diverse time series forecasting tasks, but their capacity for continuous improvement through incremental learning remains unexplored. We present the first comprehensive study investigating these…