Related papers: Multi-Granularity Framework for Unsupervised Repre…
Accurate time series forecasting is a fundamental challenge in data science. It is often affected by external covariates such as weather or human intervention, which in many applications, may be predicted with reasonable accuracy. We refer…
Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a contrastive learning paradigm featuring segregated…
Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tuning process. Currently, experimental findings based on text…
In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method is a deep metric…
Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to…
While most successful approaches for machine reading comprehension rely on single training objective, it is assumed that the encoder layer can learn great representation through the loss function we define in the predict layer, which is…
Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…
In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…
The surge in the significance of time series in digital health domains necessitates advanced methodologies for extracting meaningful patterns and representations. Self-supervised contrastive learning has emerged as a promising approach for…
This paper investigates unsupervised anomaly detection in multivariate time-series data using reinforcement learning (RL) in the latent space of an autoencoder. A significant challenge is the limited availability of anomalous data, often…
Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have…
Clustering and dimensionality reduction have been crucial topics in machine learning and computer vision. Clustering high-dimensional data has been challenging for a long time due to the curse of dimensionality. For that reason, a more…
Sparse deep learning has become a popular technique for improving the performance of deep neural networks in areas such as uncertainty quantification, variable selection, and large-scale network compression. However, most existing research…
In the context of mobile sensing environments, various sensors on mobile devices continually generate a vast amount of data. Analyzing this ever-increasing data presents several challenges, including limited access to annotated data and a…
The prevalence of wearable sensors (e.g., smart wristband) is creating unprecedented opportunities to not only inform health and wellness states of individuals, but also assess and infer personal attributes, including demographic and…
High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most…
We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series. Deconvolutional networks fully exploit the advantage the powerful expressiveness of deep neural…
Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning based approaches have mostly focused on minimising…
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additionally , we aim to disentangle the representation of time…
Multivariate time-series data are frequently observed in critical care settings and are typically characterized by sparsity (missing information) and irregular time intervals. Existing approaches for learning representations in this domain…