Matrix Factorization (MF) is a common method for generating recommendations, where the proximity of entities like users or items in the embedded space indicates their similarity to one another. Though almost all applications implicitly use a Euclidean embedding space to represent two entity types, recent work has suggested that a hyperbolic Poincar\'e ball may be more well suited to representing multiple entity types, and in particular, hierarchies. We describe a novel method to embed a hierarchy of related music entities in hyperbolic space. We also describe how a parametric empirical Bayes approach can be used to estimate link reliability between entities in the hierarchy. Applying these methods together to build personalized playlists for users in a digital music service yielded a large and statistically significant increase in performance during an A/B test, as compared to the Euclidean model.

Increased public interest in healthy lifestyles has motivated the study of algorithms that encourage people to follow a healthy diet. Applying collaborative filtering to build recommendation systems in domains where only implicit feedback is available is also a rapidly growing research area. In this report we combine these two trends by developing a recommendation system to suggest ingredients that can be added to a partial recipe. We implement the item-based collaborative filtering algorithm using a high-dimensional, sparse dataset of recipes, which inherently contains only implicit feedback. We explore the effect of different similarity measures and dimensionality reduction on the quality of the recommendations, and find that our best method achieves a recall@10 of circa 40%.

Machine learning techniques for Recommendation System (RS) and Classification has become a prime focus of research to tackle the problem of information overload. RS are software tools that aim at making informed decisions about the services that a user may like. On the other hand, classification technique deals with the categorization of a data object into one of the several predefined classes. In the multi-label classification problem, unlike the traditional multi-class classification setting, each instance can be simultaneously associated with a subset of labels. The focus of thesis is on the development of novel techniques for collaborative filtering and multi-label classification. We propose a novel method of constructing a hierarchical bi-level maximum margin matrix factorization to handle matrix completion of ordinal rating matrix. Taking the cue from the alternative formulation of support vector machines, a novel loss function is derived by considering proximity as an alternative criterion instead of margin maximization criterion for matrix factorization framework. We extended the concept of matrix factorization for yet another important problem of machine learning namely multi-label classification which deals with the classification of data with multiple labels. We propose a novel piecewise-linear embedding method with a low-rank constraint on parametrization to capture nonlinear intrinsic relationships that exist in the original feature and label space. We also study the embedding of labels together with the group information with an objective to build an efficient multi-label classifier. We assume the existence of a low-dimensional space onto which the feature vectors and label vectors can be embedded. We ensure that labels belonging to the same group share the same sparsity pattern in their low-rank representations.

Google is potentially creating a search engine for toddlers, despite recent privacy scandals. The tech giant has filed a European patent, entitled Gamifying Voice Search Experience for Children, which gives it exclusive rights to develop the concept. Aimed at nursery-age youngsters, the prospective product would use a child-friendly bubble-interface to engage with infants. This would be separate to Google Assistant, which already allows people to conduct voice-activated searches on their devices. However, education experts have raised concerns over the risk of potential privacy violations, such as those associated with Amazon's Echo Device, plus the dangers of making children addicted to technology.

We'll be talking about everyone's favorite topic at the moment: facial recognition. First San Francisco, Somerville ... now Oakland: California's Oakland has become the third US city to ban its local government using facial recognition technology, after its council passed an ordinance this week. Council member Rebecca Kaplan submitted the ordinance for city officials to consider earlier this year in June. The document describes the shortcomings of the technology and why it should be banned. "The City of Oakland should reject the use of this flawed technology on the following basis: 1) systems rely on biased datasets with high levels of inaccuracy; 2) a lack of standards around the use and sharing of this technology; 3) the invasive nature of the technology; 4) and the potential abuses of data by our government that could lead to persecution of minority groups," according to the ordinance.

We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.

A large amount of data accommodated in knowledge graphs (KG) is actually metric. For example, the Wikidata KG contains a plenitude of metric facts about geographic entities like cities, chemical compounds or celestial objects. In this paper, we propose a novel approach that transfers orometric (topographic) measures to bounded metric spaces. While these methods were originally designed to identify relevant mountain peaks on the surface of the earth, we demonstrate a notion to use them for metric data sets in general. Notably, metric sets of items inclosed in knowledge graphs. Based on this we present a method for identifying outstanding items using the transferred valuations functions 'isolation' and 'prominence'. Building up on this we imagine an item recommendation process. To demonstrate the relevance of the novel valuations for such processes we use item sets from the Wikidata knowledge graph. We then evaluate the usefulness of 'isolation' and 'prominence' empirically in a supervised machine learning setting. In particular, we find structurally relevant items in the geographic population distributions of Germany and France.

In the last decade, we have seen a qualitative jump in the performance of machine learning (ML) methods directed at narrow, well-defined tasks. For example, there has been marked progress in object recognition [57], game-playing [73], and generative models of images [40] and text [39]. Some of these methods have achieved superhuman performance within their domain [73, 64]. In each of these cases, a powerful ML model was trained using large amounts of data on a highly complex task to surpass what was commonly believed possible. Here we consider the transpose of this situation.

To the delight of binge-watchers everywhere, it's no longer prohibitively expensive to purchase a giant television. And those devices are also getting smarter, with features like voice commands, personalized recommendations, and built-in apps for Netflix and other streaming services. It's almost impossible to buy a TV without them. The average consumer might ascribe the declining price to a variant of Moore's law. "Right now, you're paying with your data, but you don't know the price," says Casey Oppenheim, CEO of Disconnect, a privacy-focused software company.

Facebook today announced the open source release of Deep Learning Recommendation Model (DLRM), a state-of-the-art AI model for serving up personalized results in production environments. DLRM can be found on GitHub, and implementations of the model are available for Facebook's PyTorch, Facebook's distributed learning framework Caffe2, and Glow C . Recommendation engines decide a lot of what people see today, whether it's content on social media sites like Facebook, ecommerce sites like Amazon, or even the first options you see on an Xbox. Last month, Amazon made its AI for the shopping recommendations system Personalize available on AWS. A paper by more than 20 Facebook AI researchers published on arXiv in late May explains how the model uses embedding tables that map categorical data to representations.