5 March 2024 in Business & Information Systems Engineering
Data-centric artificial intelligence (data-centric AI) represents an emerging paradigm that emphasizes the importance of enhancing data systematically and at scale to build effective and efficient AI-based systems. The novel paradigm complements recent model-centric AI, which focuses on improving the performance of AI-based systems based on changes in the model using a fixed set of data. The objective of this article is to introduce practitioners and researchers from the field of Business and Information Systems Engineering (BISE) to data-centric AI. The paper defines relevant terms, provides key characteristics to contrast the paradigm of data-centric AI with the model-centric one, and introduces a framework to illustrate the different dimensions of data-centric AI. In addition, an overview of available tools for data-centric AI is presented and this novel paradigm is differenciated from related concepts. Finally, the paper discusses the longer-term implications of data-centric AI for the BISE community.
29 October 2018 in Production Engineering
2 June 2023 in Proceedings of the International AAAI Conference on Web and Social Media
The storming of the U.S. Capitol on January 6, 2021 has led to the killing of 5 people and is widely regarded as an attack on democracy. The storming was largely coordinated through social media networks such as Twitter and "Parler". Yet little is known regarding how users interacted on Parler during the storming of the Capitol. In this work, we examine the emotion dynamics on Parler during the storming with regard to heterogeneity across time and users. For this, we segment the user base into different groups (e.g., Trump supporters and QAnon supporters). We use affective computing to infer the emotions in content, thereby allowing us to provide a comprehensive assessment of online emotions. Our evaluation is based on a large-scale dataset from Parler, comprising of 717,300 posts from 144,003 users. We find that the user base responded to the storming of the Capitol with an overall negative sentiment. Akin to this, Trump supporters also expressed a negative sentiment and high levels of unbelief. In contrast to that, QAnon supporters did not express a more negative sentiment during the storming. We further provide a cross-platform analysis and compare the emotion dynamics on Parler and Twitter. Our findings point at a comparatively less negative response to the incidents on Parler compared to Twitter accompanied by higher levels of disapproval and outrage. Our contribution to research is three-fold: (1) We identify online emotions that were characteristic of the storming; (2) we assess emotion dynamics across different user groups on Parler; (3) we compare the emotion dynamics on Parler and Twitter. Thereby, our work offers important implications for actively managing online emotions to prevent similar incidents in the future.
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Recent research suggests that combining AI models with a human expert can exceed the performance of either alone. The combination of their capabilities is often realized by learning to defer algorithms that enable the AI to learn to decide whether to make a prediction for a particular instance or defer it to the human expert. However, to accurately learn which instances should be deferred to the human expert, a large number of expert predictions that accurately reflect the expert's capabilities are required—in addition to the ground truth labels needed to train the AI. This requirement shared by many learning to defer algorithms hinders their adoption in scenarios where the responsible expert regularly changes or where acquiring a sufficient number of expert predictions is costly. In this paper, we propose a three-step approach to reduce the number of expert predictions required to train learning to defer algorithms. It encompasses (1) the training of an embedding model with ground truth labels to generate feature representations that serve as a basis for (2) the training of an expertise predictor model to approximate the expert's capabilities. (3) The expertise predictor generates artificial expert predictions for instances not yet labeled by the expert, which are required by the learning to defer algorithms. We evaluate our approach on two public datasets. One with "synthetically" generated human experts and another from the medical domain containing real-world radiologists' predictions. Our experiments show that the approach allows the training of various learning to defer algorithms with a minimal number of human expert predictions. Furthermore, we demonstrate that even a small number of expert predictions per class is sufficient for these algorithms to exceed the performance the AI and the human expert can achieve individually.
1 June 2022 in Production and Operations Management
Ending the HIV/AIDS epidemic is an important target of the United Nations Sustainable Development Goals (SDGs). To achieve it, countries worldwide donate large amounts of development aid (USD 15.18 billion annually). However, current practice in allocating development aid is largely based on decision heuristics and thus subject to inefficiencies. To address this problem, we aim to support managers of funding bodies in identifying cost‐effective allocations of development aid and thus develop a new decision model. We combine data analytics with mathematical optimization, whereby the former estimates the country‐specific effectiveness of aid, and the latter suggests an allocation under budget constraints. We evaluate our decision model using aid data obtained from the SDG Financing Lab of the OECD, demonstrating that our decision model could reduce the infection rate over current practice. Our work directly benefits managers of funding bodies tasked with financing development activities and helps them achieve cost‐effective progress toward ending the HIV/AIDS epidemic.
20 March 2025 in IEEE Geoscience and Remote Sensing Magazine
Over the past decades, there has been an explosion in the amount of available Earth observation (EO) data. The unprecedented coverage of Earth’s surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth system models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates because of their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC, including seminal works in its traditional applications to image and video compression domains with a focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with “natural images,” and we explain the additional challenges and opportunities they present. Additionally, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FMs) has advanced methods to efficiently distill representations from vast amounts of unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine-to-machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESMs.