Related papers: TARDIS: Mitigating Temporal Misalignment via Repre…

Multivariate time series present challenges to standard machine learning techniques, as they are often unlabeled, high dimensional, noisy, and contain missing data. To address this, we propose T-Rep, a self-supervised method to learn time…

Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials (RCTs) suffer from high cost or…

Duration modelling has become an important research problem once more with the rise of non-attention neural text-to-speech systems. The current approaches largely fall back to relying on previous statistical parametric speech synthesis…

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

Representation learning models for graphs are a successful family of techniques that project nodes into feature spaces that can be exploited by other machine learning algorithms. Since many real-world networks are inherently dynamic, with…

Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection…

We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…

Recently, high dimensional vector auto-regressive models (VAR), have attracted a lot of interest, due to novel applications in the health, engineering and social sciences. The presence of temporal dependence poses additional challenges to…

Most pictures shared online are accompanied by temporal metadata (i.e., the day and time they were taken), which makes it possible to associate an image content with real-world events. Maliciously manipulating this metadata can convey a…

Controlled text perturbation is useful for evaluating and improving model generalizability. However, current techniques rely on training a model for every target perturbation, which is expensive and hard to generalize. We present Tailor, a…

Time series classification faces two unavoidable problems. One is partial feature information and the other is poor label quality, which may affect model performance. To address the above issues, we create a label correction method to time…

Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling. Nonetheless, the non-stationarity of time series undermines the reliability of pre-trained…

Domain shift poses a fundamental challenge in time series analysis, where models trained on source domain often fail dramatically when applied in target domain with different yet similar distributions. While current unsupervised domain…

The paper describes the deep learning approach for forecasting non-stationary time series with using time trend correction in a neural network model. Along with the layers for predicting sales values, the neural network model includes a…

There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to stratify landscape based on mobility activity time series. First, the time series signal is…

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

We propose a method for adaptive nonlinear sequential modeling of vector-time series data. Data is modeled as a nonlinear function of past values corrupted by noise, and the underlying non-linear function is assumed to be approximately…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…