15 January 2022 in International Journal of Forecasting
27 February 2024 in ACM Transactions on Knowledge Discovery From Data
Domain generalization aims to design models that can effectively generalize to unseen target domains by learning from observed source domains. Domain generalization poses a significant challenge for time series data, due to varying data distributions and temporal dependencies. Existing approaches to domain generalization are not designed for time series data, which often results in suboptimal or unstable performance when confronted with diverse temporal patterns and complex data characteristics. We propose a novel approach to tackle the problem of domain generalization in time series forecasting. We focus on a scenario where time series domains share certain common attributes and exhibit no abrupt distribution shifts. Our method revolves around the incorporation of a key regularization term into an existing time series forecasting model:domain discrepancy regularization. In this way, we aim to enforce consistent performance across different domains that exhibit distinct patterns. We calibrate the regularization term by investigating the performance within individual domains and propose thedomain discrepancy regularization with domain difficulty awareness. We demonstrate the effectiveness of our method on multiple datasets, including synthetic and real-world time series datasets from diverse domains such as retail, transportation, and finance. Our method is compared against traditional methods, deep learning models, and domain generalization approaches to provide comprehensive insights into its performance. In these experiments, our method showcases superior performance, surpassing both the base model and competing domain generalization models across all datasets. Furthermore, our method is highly general and can be applied to various time series models.
22 March 2024 in International Journal of Forecasting
14 July 2026 in ACM Transactions on Recommender Systems
Machine learning-powered recommender systems help users find items they like. Issues in the interaction data processed by these systems frequently lead to problems, e.g., to the accidental recommendation of low-quality products or dangerous items. Such data issues are hard to anticipate upfront, and are typically detected post-deployment after they have already impacted the user experience. We argue that a principled data debugging process is required during which human experts identify potentially hurtful data issues and preemptively mitigate them. Recent notions of “data importance,” such as the Data Shapley value, represent a promising direction to identify training data points likely to cause issues. However, the scale of real-world interaction datasets makes it infeasible to apply existing techniques to compute the Data Shapley value in recommendation scenarios. We tackle this problem by introducing the KMC-Shapley algorithm for the scalable estimation of Data Shapley values in neighborhood-based recommendation on sparse interaction data. We conduct an experimental evaluation of the efficiency and scalability of our algorithm on both public and proprietary datasets with millions of interactions, and showcase that Data Shapley value identify impactful data points for two recommendation tasks in e-commerce. Furthermore, we discuss applications of Data Shapley values on real-world click and purchase data in e-commerce, such as identifying dangerous products or improving the ecological sustainability of product recommendations. We implement our approach in the Illoominate library and release it under an open license.