Related papers: PREP: Pre-training with Temporal Elapse Inference …

Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited by their - (i) inability to learn cross-modal…

Information cascade popularity prediction is critical for many applications, including but not limited to identifying fake news and accurate recommendations. Traditional feature-based methods heavily rely on handcrafted features, which are…

In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future state which are predictable from those which are inherently…

As the role played by statistical and computational sciences in climate and environmental modelling and prediction becomes more important, Machine Learning researchers are becoming more aware of the relevance of their work to help tackle…

Traditional regression and prediction tasks often only provide deterministic point estimates. To estimate the distribution or uncertainty of the response variable, traditional methods either assume that the posterior distribution of samples…

Modeling and predicting the popularity of online content is a significant problem for the practice of information dissemination, advertising, and consumption. Recent work analyzing massive datasets advances our understanding of popularity,…

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing…

Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner. Despite remarkable progress in recent years,…

Probabilistic models can learn users' preferences from the history of their item adoptions on a social media site, and in turn, recommend new items to users based on learned preferences. However, current models ignore psychological factors…

Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success. A renewed interest in learning choice models has led to significant…

A rich set of frequentist model averaging methods has been developed, but their applications have largely been limited to point prediction, as measuring prediction uncertainty in general settings remains an open problem. In this paper we…

State-of-the-art pretrained language models tend to perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. Recent work suggests two main reasons for this: (1) popular…

Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled…

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning…

In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is…

Pretext training followed by task-specific fine-tuning has been a successful approach in vision and language domains. This paper proposes a self-supervised pretext training framework tailored to event sequence data. We introduce a novel…

Numerous powerful point process models have been developed to understand temporal patterns in sequential data from fields such as health-care, electronic commerce, social networks, and natural disaster forecasting. In this paper, we develop…

Influence maximization is the task of finding a set of seed nodes in a social network such that the influence spread of these seed nodes based on certain influence diffusion model is maximized. Topic-aware influence diffusion models have…

Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale…

Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through…