Multi-Task Learning for Spatio-Temporal Event Forecasting

Abstract

Spatial event forecasting from social media is an important problem but encounters critical challenges, such as dynamic patterns of features (keywords) and geographic heterogeneity (e.g., spatial correlations, imbalanced samples, and different populations in different locations). Most existing approaches (e.g., LASSO regression, dynamic query expansion, and burst detection) are designed to address some of these challenges, but not all of them. This paper proposes a novel multi-task learning framework which aims to concurrently address all the challenges. Specifically, given a collection of locations (e.g., cities), we propose to build forecasting models for all locations simultaneously by extracting and utilizing appropriate shared information that effectively increases the sample size for each location, thus improving the forecasting performance. We combine both static features derived from a predefined vocabulary by domain experts and dynamic features generated from dynamic query expansion in a multi-task feature learning framework; we investigate different strategies to balance homogeneity and diversity between static and dynamic terms. Efficient algorithms based on Iterative Group Hard Thresholding are developed to achieve efficient and effective model training and prediction. Extensive experimental evaluations on Twitter data from four different countries in Latin America demonstrated the effectiveness of our proposed approach.

Joint Household Characteristic Prediction via Smart Meter Data

“…In our experiments, we evaluate the proposed DisMTRL model on two single-task learning models: KNN and IndSVM, multi-task feature learning (MTFL) [16], multi-task relationship learning (MTRL) [25] and constrained multi-task feature learning (ConMTFL) [33]. Specifically, we implement all the algorithms using MATLAB, and the codes are available at the supplement website 12 .…”

Titan

“…A handful of works started to address the urban event prediction problem on a spatiotemporal resolution. For example, Zhao et al [35] proposed a multi-task learning framework that models forecasting tasks in related geo-locations concurrently and; Gerber et al [9] utilized a logistic regression model for spatiotemporal event forecasting, the urban event predictions with true spatiotemporal resolution. One limitation of these existing studies is that the temporal dimension is considered to be independent of the spatial dimension, and any interactions between the two are ignored.…”

Multi-Task Learning Improves Disease Models from Web Search

“…We extend the standard elastic net model to a multi-task version [53]. It is specified by the following optimization task…”

“…Multi-task learning has been applied in the context of usergenerated data modeling [32,38] and computational health [9,10,19,53,54]. Given various tasks and objectives, multi-task learning frameworks can be different.…”

“…Our work, however, focuses on a collective regression task, aiming to exploit relationships at a higher level, determined by geography, rather than specific user characteristics. Finally, Zhao et al proposed a linear regularized multi-task regression model to detect civil unrest events in various locations using Twitter data [53]. In our work, apart from a different thematic focus, we also deploy nonlinear multi-task learning frameworks.…”