Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. In this paper, we propose a method for mitigating bias in classifier training by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations, while instances sharing a protected attribute are forced further apart. In such a way our method learns representations which capture the task label in focused regions, while ensuring the protected attribute has diverse spread, and thus has limited impact on prediction and thereby results in fairer models. Extensive experimental results across four tasks in NLP and computer vision show (a) that our proposed method can achieve fairer representations and realises bias reductions compared with competitive baselines; and (b) that it can do so without sacrificing main task performance; (c) that it sets a new state-of-the-art performance in one task despite reducing the bias. Finally, our method is conceptually simple and agnostic to network architectures, and incurs minimal additional compute cost.

The expansion of Fiber-To-The-Home (FTTH) networks creates high costs due to expensive excavation procedures. Optimizing the planning process and minimizing the cost of the earth excavation work therefore lead to large savings. Mathematically, the FTTH network problem can be described as a minimum Steiner Tree problem. Even though the Steiner Tree problem has already been investigated intensively in the last decades, it might be further optimized with the help of new computing paradigms and emerging approaches. This work studies upcoming technologies, such as Quantum Annealing, Simulated Annealing and nature-inspired methods like Evolutionary Algorithms or slime-mold-based optimization. Additionally, we investigate partitioning and simplifying methods. Evaluated on several real-life problem instances, we could outperform a traditional, widely-used baseline (NetworkX Approximate Solver) on most of the domains. Prior partitioning of the initial graph and the presented slime-mold-based approach were especially valuable for a cost-efficient approximation. Quantum Annealing seems promising, but was limited by the number of available qubits.

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better-improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.

Predicting metrics associated with entities' transnational behavior within payment processing networks is essential for system monitoring. Multivariate time series, aggregated from the past transaction history, can provide valuable insights for such prediction. The general multivariate time series prediction problem has been well studied and applied across several domains, including manufacturing, medical, and entomology. However, new domain-related challenges associated with the data such as concept drift and multi-modality have surfaced in addition to the real-time requirements of handling the payment transaction data at scale. In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database. We propose a model with five unique components to estimate the transaction metrics from multi-modality data. Four of these components capture interaction, temporal, scale, and shape perspectives, and the fifth component fuses these perspectives together. We also propose a hybrid offline/online training scheme to address concept drift in the data and fulfill the real-time requirements. Combining the estimation model with a graphical user interface, the prototype transaction metric estimation system has demonstrated its potential benefit as a tool for improving a payment processing company's system monitoring capability.

LONDON – Long before the real-world effects of climate change became so abundantly obvious, the data painted a bleak picture – in painful detail – of the scale of the problem. For decades, carefully collected data on weather patterns and sea temperatures were fed into models that analyzed, predicted, and explained the effects of human activities on our climate. And now that we know the alarming answer, one of the biggest questions we face in the next few decades is how data-driven approaches can be used to overcome the climate crisis. Data and technologies like artificial intelligence (AI) are expected to play a very large role. But that will happen only if we make major changes in data management.

During the pandemic, technology companies have been pitching their emotion-recognition software for monitoring workers and even children remotely. Take, for example, a system named 4 Little Trees. Developed in Hong Kong, the program claims to assess children's emotions while they do classwork. It maps facial features to assign each pupil's emotional state into a category such as happiness, sadness, anger, disgust, surprise and fear. It also gauges'motivation' and forecasts grades.

AI systems are compute-intensive: the AI lifecycle often requires long-running training jobs, hyperparameter searches, inference jobs, and other costly computations. They also require massive amounts of data that might be moved over the wire, and require specialized hardware to operate effectively, especially large-scale AI systems. All of these activities require electricity -- which has a carbon cost. There are also carbon emissions in ancillary needs like hardware and datacenter cooling [1]. Thus, AI systems have a massive carbon footprint[2]. This carbon footprint also has consequences in terms of social justice as we will explore in this article.

Apple has introduced new sharing and personalized recommendation features for Podcasts on iOS 15, all meant to help you discover new shows to listen to. Starting today, you'll find personalized recommendation sections in the Listen Now page that show you podcasts similar to the ones you enjoy. They'll be entitled "If You Like '[Show Name]'..." and then list titles in the same category or with the same theme or same format. They could also list shows from the same studio or titles other users listening to that particular podcast are also following. You'll find new sections with recommendations based the topics you usually enjoy, as well.

This research suggests an add-on to empower Google Forms to be an automatic machine for generating multiple-choice questions (MCQs) used in online assessments. In this paper, we elaborate an add-on design mainly comprising question-formulating software and data storage. The algorithm as an intellectual mechanism of this software can produce MCQs at an analytical level. In an experiment, we found the MCQs could assess levels of students' knowledge comparably with those generated by human experts. This add-on can be applied generally to formulate MCQs for any rational concepts. With no effort from an instructor at runtime, the add-on can transform a few data instances describing rational concepts to be variety sets of MCQs.

Multicomponent problems are hard to solve as each component has the potential to influence the feasibility as well as the quality of the other components [4]. Among the studied multi-component problems, vehicle routing problems with loading constraints [15] appear to be very frequently investigated. In these problems, tour are to be created for vehicles while constraints and aims of specific loading policies must be taken into account. One of these problems is the Traveling Thief Problem (TTP), which combines two classic well-known and well-studied problems: the Knapsack Problem (KP) and the Traveling Salesman Problem (TSP). The TTP was proposed in 2013 by Bonyadi et al. [3] in order to provide an academic abstraction of multi-component problems for the scientific community. In the TTP, a thief travels across all cities (TSP component) and steals items along the way (KP component).