Search for: All records

Over the past several years, a multitude of methods to measure the fairness of a machine learning model have been proposed. However, despite the growing number of publications and implementations, there is still a critical lack of literature that explains the interplay of fair machine learning with the social sciences of philosophy, sociology, and law. We hope to remedy this issue by accumulating and expounding upon the thoughts and discussions of fair machine learning produced by both social and formal (i.e., machine learning and statistics) sciences in this field guide. Specifically, in addition to giving the mathematical and algorithmic backgrounds of several popular statistics-based fair machine learning metrics used in fair machine learning, we explain the underlying philosophical and legal thoughts that support them. Furthermore, we explore several criticisms of the current approaches to fair machine learning from sociological, philosophical, and legal viewpoints. It is our hope that this field guide helps machine learning practitioners identify and remediate cases where algorithms violate human rights and values.

Video Paragraph Captioning aims to generate a multi-sentence description of an untrimmed video with multiple temporal event locations in a coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee the learnt embedding features are consistent with the captions semantics. Comprehensive experiments and extensive ablation studies on the ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms previous state-of-the-art methods in terms of accuracy and diversity. The source code is made publicly available at: https://github.com/UARK-AICV/VLTinT.

Machine learning models to predict refugee crisis situations are still lacking. The model proposed in this work uses a set of predictive features that are indicative of the sociocultural, socioeconomic, and economic characteristics that exist within each country and region. Twenty-eight features were collected for specific countries and years. The feature set was tested in experiments using ordinary least squares regression based on regional subsets. Potential location-based features stood out in our results, such as the global peace index, access to electricity, access to basic water, media censorship, and healthcare. The model performed best for the region of Europe, wherein the features with the most predictive power included access to justice and homicide rate. Corruption features stood out in both Africa and Asia, while population features were dominant in the Americas. Model performance metrics are provided for each experiment. Limitations of this dataset are discussed, as are steps for future work.