To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain. Although CDR has been extensively studied in recent years, there is a lack of a systematic review of the existing CDR approaches. To fill this gap, in this paper, we provide a comprehensive review of existing CDR approaches, including challenges, research progress, and future directions. Specifically, we first summarize existing CDR approaches into four types, including single-target CDR, multi-domain recommendation, dual-target CDR, and multi-target CDR. We then present the definitions and challenges of these CDR approaches. Next, we propose a full-view categorization and new taxonomies on these approaches and report their research progress in detail. In the end, we share several promising research directions in CDR.

Abstract: Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area.

The idea of creating a virtual human that can converse seamlessly with a user seems daunting to most people who are just getting into artificial intelligence and looking into how utterly complex existing commercial systems are. And their fears aren't misled - larger systems that contain a plethora of data samples and an intricate network architecture, and are responsible for providing the highest quality home assistant system are very difficult to replicate. But, creating virtual assistants at a smaller level has already been simplified to allow virtually anyone to make their own conversational persona. Over the past decade, the University of Southern California's Institute for Creative Technologies has developed countless virtual personalities for a variety of reasons: The institute has been able to create the amount of virtual humans as they have because of the technology they developed titled'NPCEditor'. As the name implies, the program allows the team to edit an NPC, or non-player-character. Developed by research scientist Anton Leuski and lead professor of NLP David Traum, the software has been simplified enough so that it is incredibly easy to create a virtual human.

This paper presents the first general (supervised) statistical learning framework for point processes in general spaces. Our approach is based on the combination of two new concepts, which we define in the paper: i) bivariate innovations, which are measures of discrepancy/prediction-accuracy between two point processes, and ii) point process cross-validation (CV), which we here define through point process thinning. The general idea is to carry out the fitting by predicting CV-generated validation sets using the corresponding training sets; the prediction error, which we minimise, is measured by means of bivariate innovations. Having established various theoretical properties of our bivariate innovations, we study in detail the case where the CV procedure is obtained through independent thinning and we apply our statistical learning methodology to three typical spatial statistical settings, namely parametric intensity estimation, non-parametric intensity estimation and Papangelou conditional intensity fitting. Aside from deriving theoretical properties related to these cases, in each of them we numerically show that our statistical learning approach outperforms the state of the art in terms of mean (integrated) squared error.

This paper briefly reviews the connections between meta-learning and self-supervised learning. Meta-learning can be applied to improve model generalization capability and to construct general AI algorithms. Self-supervised learning utilizes self-supervision from original data and extracts higher-level generalizable features through unsupervised pre-training or optimization of contrastive loss objectives. In self-supervised learning, data augmentation techniques are widely applied and data labels are not required since pseudo labels can be estimated from trained models on similar tasks. Meta-learning aims to adapt trained deep models to solve diverse tasks and to develop general AI algorithms. We review the associations of meta-learning with both generative and contrastive self-supervised learning models. Unlabeled data from multiple sources can be jointly considered even when data sources are vastly different. We show that an integration of meta-learning and self-supervised learning models can best contribute to the improvement of model generalization capability. Self-supervised learning guided by meta-learner and general meta-learning algorithms under self-supervision are both examples of possible combinations.

The insurance industry is a competitive sector representing an estimated $507 billion or 2.7 percent of the US Gross Domestic Product. As customers become increasingly selective about tailoring their insurance purchases to their unique needs, leading insurers are exploring how machine learning (ML) can improve business operations and customer satisfaction. The greatest opportunities seem to lie, perhaps unsurprisingly, in claims and underwriting. No other sources have taken a comprehensive look at the impact of AI among the leading insurance companies in the U.S. We researched this sector in depth to help answer questions business leaders are asking today: This article aims to present a comprehensive look at the four leading insurance companies and their use of AI. Our "top 4" rankings are based on the National Association of Insurance Commissioners' 2016 ranking of the top 25 insurance companies.

As artificial intelligence (AI)-empowered applications become widespread, there is growing awareness and concern for user privacy and data confidentiality. This has contributed to the popularity of federated learning (FL). FL applications often face data distribution and device capability heterogeneity across data owners. This has stimulated the rapid development of Personalized FL (PFL). In this paper, we complement existing surveys, which largely focus on the methods and applications of FL, with a review of recent advances in PFL. We discuss hurdles to PFL under the current FL settings, and present a unique taxonomy dividing PFL techniques into data-based and model-based approaches. We highlight their key ideas, and envision promising future trajectories of research towards new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.

There has been a paradigm-shift in urban logistic services in the last years; demand for real-time, instant mobility and delivery services grows. This poses new challenges to logistic service providers as the underlying stochastic dynamic vehicle routing problems (SDVRPs) require anticipatory real-time routing actions. Searching the combinatorial action space for efficient routing actions is by itself a complex task of mixed-integer programming (MIP) well-known by the operations research community. This complexity is now multiplied by the challenge of evaluating such actions with respect to their effectiveness given future dynamism and uncertainty, a potentially ideal case for reinforcement learning (RL) well-known by the computer science community. For solving SDVRPs, joint work of both communities is needed, but as we show, essentially non-existing. Both communities focus on their individual strengths leaving potential for improvement. Our survey paper highlights this potential in research originating from both communities. We point out current obstacles in SDVRPs and guide towards joint approaches to overcome them.

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as a loss signal to train models to produce explanations for their predictions, and as a means to evaluate the quality of model-generated explanations. In this review, we identify three predominant classes of explanations (highlights, free-text, and structured), organize the literature on annotating each type, point to what has been learned to date, and give recommendations for collecting ExNLP datasets in the future.

Despite rising levels of automation through big-data, much of the data-mining and machine learning process still relies on human intervention, introducing different biases. The amount of structured and unstructured data generated has grown exponentially over the last few decades and will continue to do so for years to come. The'big data' analytics could potentially overcome numerous challenges that corporations and governments have faced for centuries while making decisions: the lack of adequate data for formulating policies (e.g., targeting policies for a particular social group) or examining market or consumer expectations (e.g., recommendation system). The descriptive as well as predictive modeling that is driven by the big data paradigm can help decision-makers derive valuable insights for personal, commercial, or collective gains. However, the modern data collection process and algorithms remain susceptible to data mining biases. Without taking appropriate measures, the big data can amplify the negative effect of the existing social issues (e.g., racial discrimination) and render the findings worthless or even counterproductive [1], [2].