Abstract. Mapping the distribution of poverty in developing countries is essential for humanitarian organizations and policymakers to formulate targeted programs and aid. However, traditional methods for obtaining socioeconomic data can be time-consuming, expensive, and labor-intensive. Recent studies have demonstrated the effectiveness of combining machine learning and satellite images to estimate wealth in sub-Saharan African countries (Xie et al., 2016, Jean et al., 2016). In this study, we investigate the extent to which this method can be applied in the context of the Philippine archipelago to predict four different socioeconomic indicators: wealth level, years of education, access to electricity, and access to water. We also propose an alternative, cost-effective approach that leverages a combination of volunteered geographic information from OpenStreetMap and nighttime lights satellite imagery for estimating socioeconomic indicators. The best models, which incorporate regional indicators as predictors, explain approximately 63% of the variation in asset-based wealth. Our findings also indicate that models trained on publicly available, volunteer-curated geographic data achieve the same predictive performance as that of models trained using proprietary satellite images.

Meta-learning aims to learn a model that can handle multiple tasks generated from an unknown but shared distribution. However, typical meta-learning algorithms have assumed the tasks to be similar such that a single meta-learner is sufficient to aggregate the variations in all aspects. In addition, there has been less consideration of uncertainty when limited information is given as context. In this paper, we devise a novel meta-learning framework, called Meta-learning Amidst Heterogeneity and Ambiguity (MAHA), that outperforms previous works in prediction based on its ability to task identification. By extensively conducting several experiments in regression and classification, we demonstrate the validity of our model, which turns out to generalize to both task heterogeneity and ambiguity.

Meta-learning aims to learn a model that can handle multiple tasks generated from an unknown but shared distribution. However, typical meta-learning algorithms have assumed the tasks to be similar such that a single meta-learner is sufficient to aggregate the variations in all aspects. In addition, there has been less consideration on uncertainty when limited information is given as context. In this paper, we devise a novel meta-learning framework, called Meta-learning Amidst Heterogeneity and Ambiguity (MAHA), that outperforms previous works in terms of prediction based on its ability on task identification. By extensively conducting several experiments in regression and classification, we demonstrate the validity of our model, which turns out to be robust to both task heterogeneity and ambiguity.