--Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. T o transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all existing methods ignore the high-order connectivity information in cross-domain recommendation area and suffer from the domain-incompatibility problem. In this paper, we propose a Joint Spectral Convolutional Network (JSCN) for cross-domain recommendation. JSCN will simultaneously operate multi-layer spectral convolutions on different graphs, and jointly learn a domain-invariant user representation with a domain adaptive user mapping module. As a result, the high-order comprehensive connectivity information can be extracted by the spectral convolutions and the information can be transferred across domains with the domain-invariant user mapping. The domain adaptive user mapping module can help the incompatible domains to transfer the knowledge across each other . Extensive experiments on 24 Amazon rating datasets show the effectiveness of JSCN in the cross-domain recommendation, with 9 .2% Recommending users with a set of preferred items is still an open problem [1]-[6], especially when the dataset is very sparse. To remedy the data sparsity issue, broad-leraning based model [7] and cross-domain recommender system [4], [8] are proposed where the information from other source domains can be transferred to the target domain. To transfer the knowledge from one domain to another, one can use the overlapping users [4], [6], [8], [9] in two ways: (1) the neighborhood information of common users stores the structure information of different domains with which we can do cross-domain recommendation [6], [10]; or (2) we can learn a mapping function [4], [8] to project latent vectors learned in one domain into another, and thus the knowledge can be transferred.

It's no secret that government is hot on artificial intelligence as a tool to improve the citizen experience – especially given the president's recent signing …

Google unveiled a new Pixel smartphone and other hardware devices Tuesday, all aimed at getting people even more reliant on its artificial-intelligence services. NEW YORK – It's not the computers you can see that are going to matter most, it's the one you can't. At least, that's the argument Google made at their Made by Google hardware launch event here, as they unveiled a number of new products that provide intelligence or interactions in ways that blend in with the environment around us. The tech industry has been talking about this notion of "ambient computing" for some time, but it's taken advances in areas such as artificial intelligence, cloud-based services and wireless connectivity to start to make it real. To be clear, the kinds of things Google debuted at their event – from the widely expected Pixel 4 smartphone, to Pixel Bud earbuds, and updated versions of their Nest mini smart speaker (previously Google Home Mini) and Next WiFi (formerly Google WiFi) mesh routing system – have not reached cloak of invisibility-level powers. However, the refinements the company added to these products, in conjunction with the software advancements in Android and the Google Assistant, are making it easier to get access to the kinds of information we expect from our computing devices in more natural ways.

NHS Digital wanted to make it easier for users to research and access published NHS health data. To achieve that, the agency partnered with IPsoft to provide users with their own data concierge whom they call ViDA (or Virtual Digital Assistant). ViDA is an always-on conversational agent based on our industry-leading digital colleague, Amelia. Users simply tell ViDA what information they are attempting to locate using everyday language, and ViDA can take it from there. You can read more about the project in detail here from our Cognitive Project Lead for UK Healthcare, David King.

With paperless boarding passes, biometric self-service security and in some places robots to assist customers as they make their way around terminals, it is clear to see that technology is impacting the way we travel. However, as well as changing journeys themselves, technology is having a significant impact on every part of the travel process. With the announcement earlier this month that travel agency Thomas Cook had gone into administration, it is clear that even established brands are in danger of collapse. Therefore, the need to keep up with customer demands for a frictionless booking process is of high importance in the industry. Technology is one way of achieving this.

To construct a well-performing recommender offline, eliminating selection biases of the rating feedback is critical. A current promising solution to the challenge is the causality approach using the propensity scoring method. However, the performance of existing propensity-based algorithms can be significantly affected by the propensity estimation bias. To alleviate the problem, we formulate the missing-not-at-random recommendation as the unsupervised domain adaptation problem and drive the propensity-agnostic generalization error bound. We further propose a corresponding algorithm minimizing the bound via adversarial learning. Empirical evaluation using the Yahoo! R3 dataset demonstrates the effectiveness and the real-world applicability of the proposed approach.

Learning useful representations is a key ingredient to the success of modern machine learning. Currently, representation learning mostly relies on embedding data into Euclidean space. However, recent work has shown that data in some domains is better modeled by non-euclidean metric spaces, and inappropriate geometry can result in inferior performance. In this paper, we aim to eliminate the inductive bias imposed by the embedding space geometry. Namely, we propose to map data into more general non-vector metric spaces: a weighted graph with a shortest path distance. By design, such graphs can model arbitrary geometry with a proper configuration of edges and weights. Our main contribution is PRODIGE: a method that learns a weighted graph representation of data end-to-end by gradient descent. Greater generality and fewer model assumptions make PRODIGE more powerful than existing embedding-based approaches. We confirm the superiority of our method via extensive experiments on a wide range of tasks, including classification, compression, and collaborative filtering.

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.

Recent years have witnessed the great success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the ability of logical reasoning. However, the concrete ability of logical reasoning is critical to many theoretical and practical problems. In this paper, we propose Neural Logic Network (NLN), which is a dynamic neural architecture that builds the computational graph according to input logical expressions. It learns basic logical operations as neural modules, and conducts propositional logical reasoning through the network for inference. Experiments on simulated data show that NLN achieves significant performance on solving logical equations. Further experiments on real-world data show that NLN significantly outperforms state-of-the-art models on collaborative filtering and personalized recommendation tasks.

Google unveiled a new Pixel smartphone and other hardware devices Tuesday, all aimed at getting people even more dependent on its artificial-intelligence services. The Pixel 4 phone promises to respond to AI queries even faster than before, while a home Wi-Fi system is getting the AI features for the first time. The company also unveiled a new smart speaker and wireless earbuds, both invoking the AI-powered Google Assistant. The Assistant, akin to Apple's Siri and Amazon's Alexa, is now available on more than 1 billion devices, including ones made by other manufacturers. With Google's own products, though, the company can steer users to Assistant features even more.