Deep recommender systems (DRS) are intensively applied in modern web services. To deal with the massive web contents, DRS employs a two-stage workflow: retrieval and ranking, to generate its recommendation results. The retriever aims to select a small set of relevant candidates from the entire items with high efficiency; while the ranker, usually more precise but time-consuming, is supposed to further refine the best items from the retrieved candidates. Traditionally, the two components are trained either independently or within a simple cascading pipeline, which is prone to poor collaboration effect. Though some latest works suggested to train retriever and ranker jointly, there still exist many severe limitations: item distribution shift between training and inference, false negative, and misalignment of ranking order. As such, it remains to explore effective collaborations between retriever and ranker.

Conversational AI has seen an exponential rise in popularity in the last decade and has become mainstream over the past two years. Enterprise adoption of Conversational AI is accelerating. Businesses are investing millions of dollars for conversational AI applications with massive expectations to improve customer experience and operational efficiencies. Chatbots and Virtual Assistants are leveraging AI technologies to provide innovative and efficient solutions benefitting customers, employees, and partners. In this scenario, it is crucial to understand the fundamental differences between a chatbot and a more sophisticated solution like a virtual assistant.

The Era 100 is the first of a brand new line of wifi speakers from multi-room audio specialists Sonos, taking what was good about its popular longstanding One series and adding more bass and stereo sound. With a similar aesthetic to the outgoing One, it is only 2cm taller and 1cm deeper, making it pretty compact and easy to place on a cabinet or bookshelf. It requires just a power cable, connecting to your router via wifi 6 for streaming music from more than 100 different services, including Spotify and BBC Sounds, controlled from the Sonos app on your phone. In a first for Sonos's non-portable speakers, it also supports Bluetooth 5 for impromptu streaming from guest's phones or other Bluetooth devices, which works great. A button on the top turns the voice assistant on or off.

AI-powered healthcare: AI can be used to analyze medical data and assist doctors in making diagnoses and treatment plans. Smart homes and cities: AI can be used to automate household tasks and manage energy usage in smart homes, and in cities, it can be used to manage traffic flow, optimize public transportation, and enhance public safety. Autonomous vehicles: AI can power self-driving cars, trucks, and other vehicles, which can reduce traffic accidents, increase efficiency, and save time. Virtual assistants: AI-powered virtual assistants like Siri, Alexa, and Google Assistant are already widely used, but they are expected to become even more sophisticated and personalized in the future. Improved education: AI can be used to provide personalized education to students, track their progress, and identify areas where they need additional help. However, along with these advancements, AI also presents some challenges that need to be addressed.

This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a graph of textual snippets from review text, where the edges are defined by semantic similarity. This textual, memory-based approach to rating prediction enables review-based explanations for recommendations. The method is evaluated quantitatively, highlighting that leveraging text in this way outperforms both strong memory-based and model-based collaborative filtering baselines.

Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR.

Graph Convolutional Networks (GCN) have been recently employed as core component in the construction of recommender system algorithms, interpreting user-item interactions as the edges of a bipartite graph. However, in the absence of side information, the majority of existing models adopt an approach of randomly initialising the user embeddings and optimising them throughout the training process. This strategy makes these algorithms inherently transductive, curtailing their ability to generate predictions for users that were unseen at training time. To address this issue, we propose a convolution-based algorithm, which is inductive from the user perspective, while at the same time, depending only on implicit user-item interaction data. We propose the construction of an item-item graph through a weighted projection of the bipartite interaction network and to employ convolution to inject higher order associations into item embeddings, while constructing user representations as weighted sums of the items with which they have interacted. Despite not training individual embeddings for each user our approach achieves state-of-the-art recommendation performance with respect to transductive baselines on four real-world datasets, showing at the same time robust inductive performance.

A recent focal area in the space of graph neural networks (GNNs) is graph self-supervised learning (SSL), which aims to derive useful node representations without labeled data. Notably, many state-of-the-art graph SSL methods are contrastive methods, which use a combination of positive and negative samples to learn node representations. Owing to challenges in negative sampling (slowness and model sensitivity), recent literature introduced non-contrastive methods, which instead only use positive samples. Though such methods have shown promising performance in node-level tasks, their suitability for link prediction tasks, which are concerned with predicting link existence between pairs of nodes (and have broad applicability to recommendation systems contexts) is yet unexplored. In this work, we extensively evaluate the performance of existing non-contrastive methods for link prediction in both transductive and inductive settings. While most existing non-contrastive methods perform poorly overall, we find that, surprisingly, BGRL generally performs well in transductive settings. However, it performs poorly in the more realistic inductive settings where the model has to generalize to links to/from unseen nodes. We find that non-contrastive models tend to overfit to the training graph and use this analysis to propose T-BGRL, a novel non-contrastive framework that incorporates cheap corruptions to improve the generalization ability of the model. This simple modification strongly improves inductive performance in 5/6 of our datasets, with up to a 120% improvement in Hits@50--all with comparable speed to other non-contrastive baselines and up to 14x faster than the best-performing contrastive baseline. Our work imparts interesting findings about non-contrastive learning for link prediction and paves the way for future researchers to further expand upon this area.

There is growing interest in designing recommender systems that aim at being fair towards item producers or their least satisfied users. Inspired by the domain of inequality measurement in economics, this paper explores the use of generalized Gini welfare functions (GGFs) as a means to specify the normative criterion that recommender systems should optimize for. GGFs weight individuals depending on their ranks in the population, giving more weight to worse-off individuals to promote equality. Depending on these weights, GGFs minimize the Gini index of item exposure to promote equality between items, or focus on the performance on specific quantiles of least satisfied users. GGFs for ranking are challenging to optimize because they are non-differentiable. We resolve this challenge by leveraging tools from non-smooth optimization and projection operators used in differentiable sorting. We present experiments using real datasets with up to 15k users and items, which show that our approach obtains better trade-offs than the baselines on a variety of recommendation tasks and fairness criteria.

The phrases artificial intelligence and digital transformation are interlinked in today's tech world. Even if businesses only mention one, they will almost certainly be talking about both simultaneously. In short, AI now powers the next stage of digital transformation activities and software and will continue to do so, opening up new opportunities and enabling advancements that were previously impractical. When discussing artificial intelligence (AI) in engineering and manufacturing, we frequently speak to Artificial Narrow Intelligence (ANI), created to carry out particular tasks using predetermined inputs. ANI aims to use sophisticated algorithms to carry out predefined tasks, such as CAD applications, rather than mimic human thought.